# OceanToken documentation (full text)

OceanToken is one API and one prepaid balance for 400+ AI models: text (chat/reasoning), image, video, speech, transcription, embeddings and rerank, from 67 publishers including OpenAI, Anthropic, Google, DeepSeek, Qwen and ByteDance. The API is OpenAI-compatible (base URL https://api.oceantoken.ai/v1); Claude models also answer on the Anthropic Messages API (the Anthropic SDK takes https://api.oceantoken.ai and adds /v1 itself). Prices are per model, in US dollars, with no platform fee. Console: https://app.oceantoken.ai. Product site: https://oceantoken.ai. MCP server for Codex, Claude Code, Cursor and Gemini CLI: https://mcp.oceantoken.ai/mcp (install guide: https://mcp.oceantoken.ai/install).

Generated 2026-10-18 from the live service. Canonical pages: https://docs.oceantoken.ai.

## OceanToken documentation

Source: https://docs.oceantoken.ai/

OceanToken is one API and one balance for every model you use: text, images, video, speech, transcription, embeddings and rerank. It speaks the OpenAI and Anthropic APIs, so the SDKs you already have work by changing two lines.

## Start here

1. [Create an account](https://docs.oceantoken.ai/get-started/create-account) with your email.
2. [Add credits](https://docs.oceantoken.ai/get-started/add-credits) to your prepaid balance.
3. [Create an API key](https://docs.oceantoken.ai/get-started/create-api-key) with its own limit.
4. [Make your first request](https://docs.oceantoken.ai/get-started/first-request) in curl, Python or TypeScript.

## Then

- [Add OceanToken to your coding agent](https://docs.oceantoken.ai/agents/connect): Codex, Claude Code, Cursor, Gemini CLI, OpenClaw and other MCP clients, in one command. Or [run the agent itself on OceanToken](https://docs.oceantoken.ai/agents/run-on-oceantoken).
- The [console](https://docs.oceantoken.ai/console/overview), page by page.
- Every [endpoint](https://docs.oceantoken.ai/api) you can call and every [model](https://docs.oceantoken.ai/models) you can call it with, read from the live service when this page was built.
- [Errors](https://docs.oceantoken.ai/errors) and [limits](https://docs.oceantoken.ai/limits).
- [Frequently asked questions](https://docs.oceantoken.ai/faq): compatibility, pricing, free models, spending limits, coding agents.

**Two URLs to remember**
Console: `https://app.oceantoken.ai`. API base URL: `https://api.oceantoken.ai/v1`. Nothing else is needed.

## Add credits

Source: https://docs.oceantoken.ai/get-started/add-credits

OceanToken is prepaid. Requests are charged against your balance: text models at the prices listed on the [Models](https://docs.oceantoken.ai/models) page, and image, video, speech and other media at the actual cost of each request ([how you are charged](https://docs.oceantoken.ai/models#how-you-are-charged)). You can use the API while your balance is above $0. At $0 or below, every request is refused, free models included, until you add credits. See [Errors](https://docs.oceantoken.ai/errors#balance-exhausted) for what that looks like.

## How to add credits {#top-up}

1. In the console, open **Credits**.
2. Under **Add credits**, pick **$10**, **$25**, **$50** or **$100**, or type your own amount, between **$10 and $100,000** each time.
3. Choose **Add credits**. You are taken to a hosted checkout page to pay by card.
4. When payment completes you return to the console and the new balance shows under **Available balance**, and at the bottom of the sidebar.

![The Credits page](https://docs.oceantoken.ai/img/console/credits.png)

Purchased credits are valid for 12 months from the date of purchase. Credits from trial codes, promotions or gifts may expire sooner. See section 6 of the [Terms of Service](https://app.oceantoken.ai/legal/terms).

## Where the balance shows

- **Credits** at the bottom of the console sidebar, on every page.
- **Overview** shows this week's spend against it.
- **Activity** shows spend per day and per model.

Available credits are your balance minus any holds for work still in progress. Long jobs such as video generation reserve their estimated cost when they start and settle to the actual cost when they finish.

## Organizations

An organization has one wallet. Its administrator adds credits to it and can allocate a share of it to each team; a team cannot spend past its allocation, and the organization cannot spend past its wallet.

Organizations with an agreed monthly allowance do not need to add credits. Your balance is funded for you and the Credits page shows what is available.

## Create an account

Source: https://docs.oceantoken.ai/get-started/create-account

Go to **[app.oceantoken.ai/ui/signup](https://app.oceantoken.ai/ui/signup)**.

## Personal or organization

The sign-up page offers two tabs.

| | Personal | Organization |
|---|---|---|
| Who it is for | You, using the API yourself | A company or team |
| What you enter | Email | Work email and organization name |
| What you get | One account with its own balance and keys | An organization you administer, with a shared balance and the ability to invite members |

Pick **Organization** if more than one person will use OceanToken under one bill. You can invite members later from the console.

## Activate by email

1. Enter your email and submit.
2. Open the message we send you and follow the link.
3. Set a password. Your account is active the moment you do.

The link is how we confirm the address is yours, so no password exists until you set it. If the message does not arrive within a few minutes, check your spam folder, then request it again from the same page. Disposable email addresses are not accepted.

## Sign in

Sign in at **[app.oceantoken.ai/ui/login](https://app.oceantoken.ai/ui/login)** with your email and password, or choose **Continue with Google** to use a Google account with the same email.

Forgot your password? Use **[Reset your password](https://app.oceantoken.ai/ui/forgot-password)**: enter your email and we send a link to set a new one.

## Create an API key

Source: https://docs.oceantoken.ai/get-started/create-api-key

Every request carries a key. Keys belong to your account and draw on your balance; each one can have its own spending limit and expiry, so give each application its own key.

## Create one

1. In the console, open **API Keys** and choose **Create key**.
2. Fill in the form:

![The Create an API key dialog](https://docs.oceantoken.ai/img/console/api-keys-create.png)

| Field | What it does |
|---|---|
| **Name** | A label so you recognise the key later, for example `Chatbot key`. Names are unique within your account. |
| **Expiration** | When the key stops working. **Never** for a long-lived key. |
| **Credit limit** | The most this key may spend in total. It is taken from your credits, not added to them. Choose a preset, **No limit**, or **Custom amount** in whole dollars. |
| **Reset limit every** | How often the key's spend counter goes back to zero. **N/A** means the limit is a one-time total. |

3. Choose **Create**.
4. **Copy the key now.** For security it is shown once and cannot be retrieved again. If you lose it, create a new key and delete the old one.

Keys start with `sk-`.

## Use it

Send the key as a bearer token on every request:

```
Authorization: Bearer sk-...
```

## Rotate

If a key may have leaked, **Rotate key** on its page issues a new secret and keeps the old one working for 24 hours while you switch your application over. Nothing else about the key changes. See [API Keys](https://docs.oceantoken.ai/console/api-keys#rotate-a-key).

## Change or revoke

From **API Keys** you can rename a key, change its limit and expiry, or delete it. Deleting takes effect immediately; requests with that key return `401`.

Choosing a new expiration period restarts the countdown from today.

## Your first request

Source: https://docs.oceantoken.ai/get-started/first-request

Base URL: **`https://api.oceantoken.ai/v1`**. The API is OpenAI-compatible, so an OpenAI SDK needs only the base URL and your key. Claude models also answer on the Anthropic messages API; the Anthropic SDK adds `/v1` itself, so it takes `https://api.oceantoken.ai` ([below](#claude-with-the-anthropic-sdk)).

Every sample on this page is a file we run against the service before publishing. Set `OCEANTOKEN_API_KEY` to your key and they run as-is.

  
    (code sample: https://docs.oceantoken.ai/get-started/first-request)
  
  
    (code sample: https://docs.oceantoken.ai/get-started/first-request)
  
  
    (code sample: https://docs.oceantoken.ai/get-started/first-request)
  

A successful response is the standard chat completion object: the answer under `choices[0].message.content`, and `usage` with the token counts you were billed for.

## Stream the answer

For anything a person is waiting on, stream. Tokens arrive as they are generated, and long answers do not run into the request timeout described in [Limits](https://docs.oceantoken.ai/limits).

(code sample: https://docs.oceantoken.ai/get-started/first-request)

## Claude with the Anthropic SDK

(code sample: https://docs.oceantoken.ai/get-started/first-request)

## See what you can call

(code sample: https://docs.oceantoken.ai/get-started/first-request)

The list reflects your key: if your account is limited to certain models, only those appear. The full catalog with prices is on the [Models](https://docs.oceantoken.ai/models) page and in the console.

## Next

- Pick a model on the [Models](https://docs.oceantoken.ai/models) page; the name in the table is the `model` value.
- Every endpoint, including images, video, speech and embeddings, is on the [API](https://docs.oceantoken.ai/api) page.
- [Add OceanToken to your coding agent](https://docs.oceantoken.ai/agents/connect): Codex, Claude Code, Cursor and more.
- Watch the request land in the console under **Logs**, with its cost and latency.

## Profile

Source: https://docs.oceantoken.ai/console/account

Your email address, a copy of your data, and closing your account.

![The Profile page: email address, export my data, close account](https://docs.oceantoken.ai/img/console/account.png)

## Email address

The card shows the email your account is registered under. To change it, type the new address and choose **Change email**. We send a confirmation link to the new address, and your email changes only after you click it.

## Export my data

**Download my data** saves a JSON copy of your account data: your profile, API keys, usage summary and memberships.

## Close account

**Close my account** deactivates your account. Your keys stop working immediately. An administrator can reactivate it later.

Closing does not delete the records stored for your account. To have them deleted, write to support@oceantoken.ai, as the [privacy policy](https://app.oceantoken.ai/legal/privacy) describes.

## Password

The Profile page has no password setting. To change your password, sign out and use **[Reset your password](https://app.oceantoken.ai/ui/forgot-password)**: enter your email and we send a link to set a new one.

## Sign out

**Log out**, from the menu next to your email at the bottom of the sidebar, ends the session in this browser only. Keys keep working.

## Activity

Source: https://docs.oceantoken.ai/console/activity

Your usage across models over the last **7 days** or **30 days**.

![The Activity page: totals, token breakdown, daily spend, top models and keys](https://docs.oceantoken.ai/img/console/activity.png)

## What you see

- **Spend**, **Requests** (split into ok and failed), **Tokens** and **Avg / request** for the period.
- **Input tokens**, **Output tokens**, **Cache read tokens** and **Cache write tokens**. Cached prompt tokens are the part of a repeated long prompt the model served from its cache; they are billed at the model's cached rate.
- **Daily spend**: one point per day. Days with no requests show as zero, so gaps are real gaps.
- **Top models** and **Top API keys**: where the spend went, by model and by key.

## Typical use: find what a spike cost

1. Find the day on the **Daily spend** line.
2. Check **Top models** and **Top API keys** for the same period to see which model and which application drove it.
3. Open [Logs](https://docs.oceantoken.ai/console/logs) for that day to see the individual requests.

## API

Source: https://docs.oceantoken.ai/console/api

Everything you need to call OceanToken from code, on one page.

![The API page: base URL and quickstart](https://docs.oceantoken.ai/img/console/api.png)

## Base URL

`https://api.oceantoken.ai/v1`. Point any OpenAI-compatible client at it; **Copy** puts it on your clipboard. The Anthropic SDK is the one exception: it adds `/v1` itself, so for Claude models through that SDK use `https://api.oceantoken.ai` (see [your first request](https://docs.oceantoken.ai/get-started/first-request#claude-with-the-anthropic-sdk)).

## Quickstart

Pick a **Model** and a **Language** and the page writes a runnable snippet for that model on the endpoint it is served from. Replace the placeholder with a key from [API Keys](https://docs.oceantoken.ai/console/api-keys), **Copy code**, and run it.

## Endpoints

Below the quickstart, the table lists the endpoints your account can call right now. It is derived from the live catalog, so an endpoint appears only when a model behind it is deployed. The same table, with more detail, is on the [API reference](https://docs.oceantoken.ai/api) page here.

## API Keys

Source: https://docs.oceantoken.ai/console/api-keys

Create and manage the keys your applications use.

![The API Keys list](https://docs.oceantoken.ai/img/console/api-keys.png)

## The list

| Column | Meaning |
|---|---|
| **Key ID** | Opens the key to edit it |
| **Key alias** | The name you gave it |
| **Secret key** | The last characters of the key, for telling keys apart. The full key is never shown again |
| **Created at** / **Last active** | When it was made and when it last made a request |
| **Expires** | The expiration you set, or **Never** |
| **Spend (USD)** / **Budget** | What the key has spent against its credit limit |

A key that has hit its credit limit or passed its expiration stays in the list but stops working.

## Create a key

Choose **Create key**. The form has four fields:

![The Create an API key dialog](https://docs.oceantoken.ai/img/console/api-keys-create.png)

| Field | What it does |
|---|---|
| **Name** | A label so you recognise the key later, for example `Chatbot key`. Names are unique within your account. |
| **Expiration** | When the key stops working. Pick **Never** for a long-lived key. |
| **Credit limit** | The most this key may spend in total. It is taken from your credits, not added to them. Choose a preset, **No limit**, or **Custom amount** in whole dollars. |
| **Reset limit every** | How often the key's spend counter goes back to zero. **N/A** makes the limit a one-time total. Your credit balance is not affected. |

Choose **Create**, then **copy the key immediately**: for security it is shown once and cannot be retrieved again. If you lose it, create a new key and delete the old one.

## Typical use: give a new project its own key

Name the key after the project, set a **Credit limit** you are comfortable losing if the key leaks, and choose whether the limit resets monthly. One key per application means a leaked key can be deleted without touching anything else, and Logs and Activity show what each application spends.

## Rotate a key

Rotating replaces the key's secret without touching anything else about it. Use it when a secret may have leaked, or on a schedule.

1. Open the key from its **Key ID** and choose **Rotate key**.
2. Read what will happen, then confirm. The new secret is shown once; copy it into your application.
3. Update your application. **The old secret keeps working for 24 hours**, so you can switch over without downtime. After that it stops working and requests with it return `401`.

Spend, credit limit, reset period, expiration and name stay exactly as they were: it is the same key with a new secret, so your logs and usage stay in one place.

Keys are created, edited, rotated and deleted only here in the console, signed in to your account. An API key cannot manage keys, not even itself: a key-management request made with an API key is refused with `403 forbidden`. If a key is being misused, delete it rather than rotate it: a deleted key stops working at once, while a rotated key's old secret keeps working for 24 hours.

## Edit and delete

Open a key from its **Key ID** to rename it, change its limit or reset period, or set a new expiration. Choosing a new period restarts the countdown from today; you can also keep the current expiry. Deletion is immediate: requests using the key return `401` from then on.

## Chat

Source: https://docs.oceantoken.ai/console/chat

Talk to any text model, generate images and videos, run deep research, and work with your files, all in the browser and all on the same balance and prices as the API. Chat is a working assistant, not a demo: a model that behaves well here behaves the same way through the API, because it is the same call.

![A new chat: the three quick starts and the composer](https://docs.oceantoken.ai/img/console/chat-empty.png)

## Ask a question

Type and press Enter. The model selector at the top left starts on **Smart (Auto)**, which chooses a model for each message based on how demanding it is; pick a specific model instead whenever you want one. The answer streams in as it is generated, and the footer of each answer shows which model produced it, time to first token, and tokens in and out.

## Modes

Choose **+** at the left of the composer, or one of the quick starts on a new chat.

![The + menu: files, image, video, deep research, code interpreter](https://docs.oceantoken.ai/img/console/chat-tools-menu.png)

| Mode | What it does |
|---|---|
| **Add photos & files** | Attach images, PDFs or a spreadsheet and ask about them. Attaching a spreadsheet switches to a model that can analyse it. |
| **Create image** | Describe an image and get one back. |
| **Create video** | Describe a video; it renders in the background and you are told when it is ready. |
| **Deep research** | A cited report researched from the web. Slower, but thorough. |
| **Code interpreter** | Have the model run code and produce Word, Excel or PowerPoint files and charts. |

A mode shows as a chip in the composer; the **×** on the chip returns to a normal chat.

### Create image

![Image mode: model, ratio and count in the composer](https://docs.oceantoken.ai/img/console/chat-image-mode.png)

The model selector switches to an image model; change it to any other image model. Set the **Ratio** (square, portrait or landscape), how many images to make at once, and, where the model offers them, the **Quality** and **Resolution** tiers. Then describe the image.

![A generated image with its download control](https://docs.oceantoken.ai/img/console/chat-image-result.png)

Each image has a download control. To edit an image instead, attach it and describe the change: the placeholder switches to *Describe how you want to edit the attached image*.

### Create video

![Video mode: mode, duration, size and ratio](https://docs.oceantoken.ai/img/console/chat-video-mode.png)

Pick a video model, then set **Mode** (text to video, or start from a first frame, first and last frame, or reference images, video and audio, depending on what the model supports), **Duration**, **Size** and **Ratio**, and describe the video. Rendering takes minutes, so the job runs in the background: keep working, and the **Background tasks** tray tells you when the video is ready. The estimated cost is held against your balance while it renders and settled when it finishes.

### Deep research

![Deep research mode selected in the composer](https://docs.oceantoken.ai/img/console/chat-research-mode.png)

State the topic. Before starting, the assistant may ask a few clarifying questions; answer them or skip to use defaults. Research runs in the background for several minutes, browsing the web and writing a report with sources, and notifies you when it is complete. Like video, its estimated cost is held while it runs.

### Add photos & files

Attach images or PDFs to ask about them, or a spreadsheet to have it analysed. You can also drop a file onto the composer. Files cannot be attached while an image, video or research mode is active; switch back to chat first.

## Conversations

Conversations are saved to your account. **New chat** starts one; **History** lists them, so you can continue one from another device, and each conversation's menu offers **Rename**, **Export** and **Delete**. Images and files in a conversation are kept for 30 days; after that the conversation keeps its text, but they no longer display.

## Credits

Source: https://docs.oceantoken.ai/console/credits

Your prepaid balance. The walkthrough is in [Add credits](https://docs.oceantoken.ai/get-started/add-credits).

![The Credits page: balances and Add credits](https://docs.oceantoken.ai/img/console/credits.png)

## Balances

| Card | Meaning |
|---|---|
| **Available balance** | What new requests can spend: wallet balance minus holds |
| **Wallet balance** | Credits added minus usage |
| **In-flight holds** | Estimated cost of jobs still running, such as video generation; released when they finish |

## Add credits {#buy-credits}

Pick **$10**, **$25**, **$50**, **$100** or type your own amount, then choose **Add credits**. Each amount is between $10 and $100,000. You are sent to a hosted checkout page to pay by card, and your balance updates a few seconds after payment. Purchased credits are valid for 12 months from the date of purchase (section 6 of the [Terms of Service](https://app.oceantoken.ai/legal/terms)).

## Organization wallet

If you administer an organization you also see its wallet: credits added, **Used this period** across all teams, and the **Org available balance**. Under **Per-team allocation** you can set each team's cap. A team spends at most its allocation; the organization spends at most its wallet.

## Logs

Source: https://docs.oceantoken.ai/console/logs

Every request made with your keys, newest first, for the last **24 hours** or **7 days**.

![The Logs list with successful and failed requests](https://docs.oceantoken.ai/img/console/logs.png)

## The list

| Column | Meaning |
|---|---|
| **Time** | When the request started |
| **Model** | The `model` you sent |
| **Input** / **Output** | Tokens in and out |
| **Cost** | What the request was charged. Amounts under $0.0001 are shown as `< $0.0001` rather than rounded to zero |
| **Status** | **Success** or **Failed** |

## Request details

Open a row for the full record: **Request ID**, when it **Started**, **Latency**, time to **First token** and **Throughput** in tok/s for streamed requests, **Tokens**, whether it was **Streaming**, whether the prompt **Cache** was a **Hit** or **Miss**, which **API key** made it, and the **Session** it belonged to. The **Request** and **Response** bodies are shown when they were recorded.

## Typical use: debug a failed call

1. Find the **Failed** row around the time it happened.
2. Open it. The **Response** shows the error body the API returned; [Errors](https://docs.oceantoken.ai/errors) explains each one.
3. Copy the **Request ID** if you write to us about it.

Logs show your own requests only. Nobody else's traffic appears here, and nothing about how a request was routed is exposed.

## Models

Source: https://docs.oceantoken.ai/console/models

Every model you can call, with its price in the unit you are billed in. This page is always current. The [Models](https://docs.oceantoken.ai/models) reference page here reads the same catalog, as of the date shown above its table.

![The Models page with type filters and model cards](https://docs.oceantoken.ai/img/console/models.png)

## Find a model

- **Search** by name.
- Filter by **type**; each chip shows how many models it holds: Text, Image, Video, Speech, Transcription, Embeddings, Rerank, Decisions, Audio.
- Every card shows its capability chips: **Tools**, **Reasoning**, **Vision**.

## Read a card

| Shown | Meaning |
|---|---|
| `$0.85 / $1.70 / 1M` | Input and output price per million tokens |
| `/ image` | Price per generated image |
| `/ megapixel` | Image: price per megapixel of output; **first MP, then $x / MP** when each further megapixel costs less |
| `/ search unit` | Rerank: price per search unit |
| `/ 1K chars` | Speech: price per thousand characters of input text |
| `/ min` | Transcription: price per minute of audio |
| `from … / s` | Video: price per second of output, from the lowest resolution and mode |
| **Cached input**, **Cache write** | Price per million prompt tokens read from, and written into, the cache, on models that have them |
| **Billed at the model it picks** | `smart-router`: each request is billed at the price of the model it picks |
| `131K context` | The largest input the model accepts, in tokens |
| **Free · rate-limited** | No charge; throughput is limited and not guaranteed |
| **Price TBD** | Callable now. Its price has not been published yet, so calls are free until it is; the price applies from the moment it appears here, never retroactively |

The name on the card is the exact `model` value to send. Opening a model shows every price it has, including the one-hour cache write where there is one. How each kind of model is charged is on the [Models](https://docs.oceantoken.ai/models#how-you-are-charged) reference page.

## Typical use: pick a model and try it

Choose **Try in playground** on a text model to open [Chat](https://docs.oceantoken.ai/console/chat) with it selected.

## Overview

Source: https://docs.oceantoken.ai/console/overview

The console lives at **[app.oceantoken.ai](https://app.oceantoken.ai)**. Overview is the page you land on after signing in.

![The console Overview page: this week's usage and quick actions](https://docs.oceantoken.ai/img/console/overview.png)

## This week's usage

Three numbers for the current week: **Spend**, **Requests** and **Tokens**. **View activity** opens the [Activity](https://docs.oceantoken.ai/console/activity) page for the day-by-day picture.

## Quick actions

Cards for the things you do most:

| Card | Takes you to |
|---|---|
| **Create an API key** | [API Keys](https://docs.oceantoken.ai/console/api-keys) |
| **Call the API** | [API](https://docs.oceantoken.ai/console/api): base URL, example code and every endpoint |
| **Browse models** | [Models](https://docs.oceantoken.ai/console/models): every model and its price |
| **Add credits** | [Credits](https://docs.oceantoken.ai/console/credits): add credits to your prepaid balance |
| **Open the playground** | [Chat](https://docs.oceantoken.ai/console/chat): try a model in the browser |
| **Check your usage** | [Activity](https://docs.oceantoken.ai/console/activity) |

## Navigation

The left sidebar lists every page. Your **Credits** balance sits at the bottom of the sidebar, so you can see it from any page, and the **English** control at the top right switches the interface language.

## Add OceanToken to your coding agent

Source: https://docs.oceantoken.ai/agents/connect

OceanToken has an MCP server and a plugin for coding agents. With them your agent can search the model catalog, check what a request will cost, generate images, video and voice-overs, transcribe audio, and hand a sub-task to another model, all billed to your OceanToken balance.

This adds tools; the agent keeps its own model. To run the agent itself on OceanToken models, see [Run your agent on OceanToken](https://docs.oceantoken.ai/agents/run-on-oceantoken).

The plugin, the command-line installer and their manifests are open source at [github.com/NextFormAI/oceantoken-plugins](https://github.com/NextFormAI/oceantoken-plugins).

## What your agent gets

| Tool | What it does |
|---|---|
| `search_models` | Search the catalog by name, type, publisher, capability and price |
| `get_model` | Pricing, limits, and the sizes, durations and inputs a model accepts |
| `estimate_cost` | What a request will cost before it runs, and whether your balance covers it |
| `generate_image` | Text-to-image and image edits, with previews and download links |
| `create_video` and `get_job` | Video from text, from a first (and last) frame, or from reference media |
| `generate_speech` | Voice-overs and narration |
| `transcribe_audio` | Transcripts and SRT or VTT subtitles |
| `ask_model` | Hand a sub-task to another model: a cheaper one, or a second opinion |
| `upload_file` | Use local files as references |
| `get_account` | Balance, available balance and spend |

Three skills teach the agent to use them well: `oceantoken-media` produces images, video and audio for a project, `oceantoken-models` chooses, prices and delegates, and `oceantoken-setup` runs Codex or Claude Code itself on OceanToken or wires up your app.

## Connect with one command

Ask your agent:

> Install OceanToken for me by following https://mcp.oceantoken.ai/install

or run it yourself in a terminal:

```bash
npx -y @oceantoken/cli@latest connect <client>
```

It needs Node.js 18.17 or newer. `<client>` is one of:

| Client | `<client>` | Sign-in |
|---|---|---|
| Codex (CLI or app) | `codex` | The command opens your browser and waits |
| Claude Code (terminal, IDE extension or desktop app) | `claude-code` | The command opens your browser and waits |
| Cursor | `cursor` | In Cursor, under **Settings → Tools & MCP** |
| Gemini CLI | `gemini` | In Gemini CLI: `/mcp auth oceantoken` |
| OpenClaw | `openclaw` | The command opens your browser and waits |
| OpenCode | `opencode` | The command opens your browser and waits |
| VS Code (GitHub Copilot) | `vscode` | In VS Code, when the server starts |
| WorkBuddy | `workbuddy` | In WorkBuddy |
| Hermes Agent | `hermes` | The command opens your browser and waits |
| Windsurf / Devin Desktop | `windsurf` | In Cascade |

Every client gets the MCP server and the three skills, except Windsurf, which has no skills folder and gets the server only.

What the command changes:

- Codex, Claude Code, Gemini CLI and OpenClaw get the plugin, installed with the client's own command line. With `--api-key`, Codex, Claude Code and Gemini CLI get one `oceantoken` entry in their config file instead.
- The other clients get one `oceantoken` entry in their MCP config file. Existing entries are kept, and a file with comments in it is never rewritten: you get the snippet to paste instead.
- Before the command first changes a config file it copies it to `<file>.bak-oceantoken`, and it never overwrites that copy, so your original survives any number of connects and disconnects. Each later change also leaves `<file>.bak-oceantoken-<UTC time>` with the file as it was just before. A backup is a plain copy: if the file held a key, so does the backup.
- Skills go into the client's own skills folder.

Running it again is safe; it updates what it installed. It ends with a summary: **Result** `connected` means you are done, and `incomplete` lists what is left under **Next**, such as signing in from the app or restarting the session.

### Options

```text
--api-key <key|->   Use an API key instead of OAuth sign-in ("-" reads it from stdin)
--use-env-key       Use the key in OCEANTOKEN_API_KEY
--no-login          Configure only; do not start the sign-in
--no-skills         Do not install the OceanToken skills
--dry-run           Show what would change without changing anything
--json              Print the report as JSON
--url <mcp-url>     MCP endpoint (default https://mcp.oceantoken.ai/mcp)
```

`npx -y @oceantoken/cli@latest clients` lists the supported clients and which ones are installed on this machine.

## Sign in

Signing in is OAuth. The sign-in page offers two ways to connect:

- **Sign in** with your OceanToken email and password. This creates an API key for the connecting app, which you can see and revoke under [API Keys](https://docs.oceantoken.ai/console/api-keys) in the console. New users can create an account from the same page.
- **API key**: paste a key you already have. Give it a credit limit if you want a cap on what the agent can spend.

Revoking the key disconnects the agent immediately.

To connect with a key and no browser, pass it on stdin so it stays out of your shell history. The command never puts the key on another program's command line and never prints it: it writes it only into the client's config file (OpenClaw receives it on stdin and writes its own config):

```bash
printf %s "$OCEANTOKEN_API_KEY" | npx -y @oceantoken/cli@latest connect <client> --api-key -
```

## Set it up by hand

The same result as the command, client by client.

### Codex

```bash
codex plugin marketplace add NextFormAI/oceantoken-plugins
codex plugin add oceantoken@oceantoken
codex mcp login oceantoken
```

The last command opens the sign-in page. In the Codex app you can also add the marketplace, then install **OceanToken** from the Plugins panel and sign in when asked.

### Claude Code

```text
/plugin marketplace add NextFormAI/oceantoken-plugins
/plugin install oceantoken@oceantoken
/mcp
```

In `/mcp`, choose `plugin:oceantoken:oceantoken` and select **Authenticate**.

### Claude desktop app and claude.ai

**Settings → Connectors → Add custom connector**, URL `https://mcp.oceantoken.ai/mcp`, then **Connect**. This adds the tools; the skills come with the Claude Code plugin.

### Cursor

[Add the MCP server to Cursor](https://cursor.com/install-mcp?name=oceantoken&config=eyJ1cmwiOiJodHRwczovL21jcC5vY2VhbnRva2VuLmFpL21jcCJ9). Cursor asks you to sign in the first time a tool runs. To get the skills as well, install the plugin from the repository, which has a Cursor marketplace manifest, or use the command above.

### Gemini CLI

```bash
gemini extensions install https://github.com/NextFormAI/oceantoken-plugins
```

Then, inside Gemini CLI, run `/mcp auth oceantoken` and sign in. The extension brings the MCP server and the three skills.

### OpenClaw

```bash
openclaw plugins install clawhub:@oceantoken/oceantoken --accept-capabilities
openclaw mcp set oceantoken '{"url":"https://mcp.oceantoken.ai/mcp","transport":"streamable-http","auth":"oauth"}'
openclaw mcp login oceantoken
```

The package brings the three skills. `mcp set` registers the server with OpenClaw so that `mcp login` can sign you in.

### Any other MCP client

The server is `https://mcp.oceantoken.ai/mcp`, over streamable HTTP. It supports OAuth with dynamic client registration, so most clients need only the URL:

```json
{
  "mcpServers": {
    "oceantoken": { "type": "http", "url": "https://mcp.oceantoken.ai/mcp" }
  }
}
```

To use an API key instead, send it as a bearer token:

```bash
# Codex, without the plugin
export OCEANTOKEN_API_KEY=sk-...
codex mcp add oceantoken --url https://mcp.oceantoken.ai/mcp --bearer-token-env-var OCEANTOKEN_API_KEY

# Claude Code, without the plugin
claude mcp add --transport http oceantoken https://mcp.oceantoken.ai/mcp \
  --header "Authorization: Bearer $OCEANTOKEN_API_KEY"
```

The server is also in the official MCP Registry as `ai.oceantoken/mcp`, so clients that browse the registry can find it by name.

## Make your agent use it

Agents choose their own tools. They reach for OceanToken for what they cannot do themselves, such as video, voice-overs, subtitles and cost estimates. For anything else, ask for it by name:

- `$oceantoken-media ...` in Codex, `/oceantoken:oceantoken-media ...` in Claude Code, or simply "use OceanToken to ...".
- Or make it a project rule in `AGENTS.md` (Codex) or `CLAUDE.md` (Claude Code):

  ```markdown
  Generate images, video, voice-overs and subtitles with the OceanToken tools.
  Estimate the cost first and ask me before spending more than $2.
  ```

## Costs

What the tools generate is charged to your balance at the same prices as the API; see [Models](https://docs.oceantoken.ai/models#how-you-are-charged). Ask the agent for an estimate first: that is what `estimate_cost` is for. Video jobs hold their estimated cost when they start and charge the actual cost when they finish, and failed jobs are not charged. Every request appears in the console under [Logs](https://docs.oceantoken.ai/console/logs).

## Remove it

```bash
npx -y @oceantoken/cli@latest disconnect <client>
```

This removes only what `connect` added. To cut access at once, revoke the agent's key under [API Keys](https://docs.oceantoken.ai/console/api-keys).

## Run your coding agent on OceanToken

Source: https://docs.oceantoken.ai/agents/run-on-oceantoken

Point the agent's own model at OceanToken and its requests run on your OceanToken key and balance, with any suitable model from the [Models](https://docs.oceantoken.ai/models) page. This is separate from [adding OceanToken's tools](https://docs.oceantoken.ai/agents/connect) to an agent; you can do either or both.

## Before you start

1. [Create an API key](https://docs.oceantoken.ai/get-started/create-api-key) for the agent and give it a **Credit limit**. Agents send many requests, and the limit caps what this one can spend.
2. Keep the key in an environment variable, never in a file in your repository:

   ```bash
   export OCEANTOKEN_API_KEY=sk-...
   ```

3. Check it:

   ```bash
   curl -s https://api.oceantoken.ai/v1/models -H "Authorization: Bearer $OCEANTOKEN_API_KEY" | head -c 300
   ```

## Codex

Codex 0.135 and later keep each profile in its own file next to `config.toml` (check with `codex --version`). Two additions put OceanToken one flag away and leave your default setup as it is. Back up `~/.codex/config.toml` before you edit it.

1. Append the provider to `~/.codex/config.toml`. On its own it changes nothing:

   ```toml
   [model_providers.oceantoken]
   name = "OceanToken"
   base_url = "https://api.oceantoken.ai/v1"
   env_key = "OCEANTOKEN_API_KEY"
   wire_api = "responses"
   ```

2. Create `~/.codex/oceantoken.config.toml` with two lines and no table header:

   ```toml
   model_provider = "oceantoken"
   model = "openai/gpt-5.5"
   ```

Run Codex with `codex --profile oceantoken`, and check the setup with:

```bash
codex exec --skip-git-repo-check --profile oceantoken "Reply with the single word OK"
```

Plain `codex`, without `--profile`, runs your usual setup, so that is how you switch back. To remove OceanToken, delete `oceantoken.config.toml` and the `[model_providers.oceantoken]` table.

- **Set up from an earlier version of this page?** Delete the `[profiles.oceantoken]` table from `config.toml`. Codex 0.135 and later refuse `--profile oceantoken` while it is there.
- **Codex 0.134 or earlier** has no profile files: put the same two lines under a `[profiles.oceantoken]` table in `config.toml` instead.
- **OceanToken as the default, with no flag:** put the two lines at the top of `config.toml`, above the first `[table]`, in place of any `model` or `model_provider` line already there. To switch back, restore those lines from your backup.

Codex runs tools on almost every turn, so choose a model that handles tool calls well; OpenAI GPT-5 family models are the safe choice. Avoid `aion-labs/aion-2.0` for Codex and other agents that run tools: after a tool call it tends to write its final answer into its reasoning, so the turn shows no answer. It is fine for plain chat.

## Claude Code

Claude Code speaks the Anthropic Messages API, which OceanToken serves for its Claude models. For one project, put this in `.claude/settings.local.json`, which git ignores; for every project, in `~/.claude/settings.json`:

```json
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.oceantoken.ai",
    "ANTHROPIC_AUTH_TOKEN": "<your OceanToken key>",
    "ANTHROPIC_MODEL": "anthropic/claude-sonnet-5",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "anthropic/claude-haiku-4.5"
  }
}
```

`ANTHROPIC_BASE_URL` has no `/v1`: like the Anthropic SDK, Claude Code adds it itself. Use model names exactly as the [Models](https://docs.oceantoken.ai/models) page lists them. Check the setup with:

```bash
claude -p "Reply with the single word OK"
```

The settings file holds the key in plain text. Prefer the project-local file, keep it out of git, and remember where it is.

## Other tools

Any tool that lets you set an OpenAI-compatible base URL and key works the same way: base URL `https://api.oceantoken.ai/v1`, your OceanToken key, and a model name from the [Models](https://docs.oceantoken.ai/models) page. A tool that speaks the Anthropic API takes `https://api.oceantoken.ai` and a Claude model.

## Costs

Every request the agent makes is an ordinary API request: charged to your balance at the model's price and listed in the console under [Logs](https://docs.oceantoken.ai/console/logs). Agents resend long prompts on every turn, so the **Cached input** price on the [Models](https://docs.oceantoken.ai/models) page matters as much as the input price. If a key may have leaked, [rotate it](https://docs.oceantoken.ai/console/api-keys#rotate-a-key).

## API reference

Source: https://docs.oceantoken.ai/api

Base URL **`https://api.oceantoken.ai/v1`**. Authenticate with `Authorization: Bearer sk-...`. Paths on this page are written out in full, so `/v1/chat/completions` is `https://api.oceantoken.ai/v1/chat/completions`.

## Which API shape

OceanToken does not invent request formats for models. Each model endpoint follows one existing API, named in the **Shape** column below, so the matching official SDK works with only the base URL and key changed:

| Shape | Endpoints | Use |
|---|---|---|
| **OpenAI** | chat completions, responses, images, video, embeddings, speech, transcription, models | The OpenAI SDK with `base_url="https://api.oceantoken.ai/v1"` |
| **Anthropic** | `/v1/messages` | The Anthropic SDK with `base_url="https://api.oceantoken.ai"`, for Claude models. That SDK adds `/v1` itself |
| **Cohere** | `/v1/rerank` | Cohere's rerank request: `query`, `documents`, `top_n` |
| **OceanToken** | `/v1/usage/{request_id}` | Our own, and the only one: what a request cost. See [What a request cost](#what-a-request-cost) |

Within a shape, a parameter the chosen model does not support is dropped and the request runs without it. This is what lets one request body work across every model: `top_k` is meaningful to Claude and not to GPT, `logit_bias` the other way round, and a request carrying either still succeeds on both. Nothing is rewritten, and a parameter the model does support always reaches it.

The consequence is worth stating plainly: **a successful response is not evidence that every parameter you sent took effect.** When you depend on one, check the response for it rather than the absence of an error - `tool_calls` for a function call, `tools` echoed back for a hosted tool, `response_format` honoured in the content. A capability a model does not have is not reported as an error, because for most callers that would turn a portable request into a model-specific one.

Check this once at integration time, with the model you will use, rather than discovering in production that a parameter you rely on was never applied.

## Endpoints

(the endpoint table: https://docs.oceantoken.ai/api)

The **Models** column opens the [Models](https://docs.oceantoken.ai/models) page filtered to the models that endpoint serves, with their prices; a model's type tells you which endpoint to call.

## Text

`/v1/chat/completions` is the endpoint most clients use, and the one the [first request](https://docs.oceantoken.ai/get-started/first-request) shows. `/v1/responses` is the newer stateful API with the same models. Claude models answer on `/v1/messages` with the Anthropic SDK unchanged.

### Streaming

Set `"stream": true` on any text endpoint to receive tokens as they are generated. The response is server-sent events (`Content-Type: text/event-stream`), each event a `data:` line carrying one JSON chunk in the same format the shape's SDK expects, and the stream ends with `data: [DONE]`. To receive token counts at the end of a chat-completions stream, send `"stream_options": {"include_usage": true}`; the last chunk before `[DONE]` then carries `usage`. Responses and Messages streams include usage in their own final events. Errors during a stream are described in [Errors](https://docs.oceantoken.ai/errors#errors-while-streaming).

## Images

(code sample: https://docs.oceantoken.ai/api)

The response contains a URL for each image. Download it promptly; URLs are not permanent. For edits, send the source image and an optional mask to `/v1/images/edits`.

## Video

Video is asynchronous. Submit a job, poll its status, then download the file.

(code sample: https://docs.oceantoken.ai/api)

A job moves through **`queued` → `in_progress` → `completed`** or **`failed`**. `POST /v1/videos` returns the job with its `id` and initial state; `GET /v1/videos/{video_id}` returns the current state, and once it is `completed`, `GET /v1/videos/{video_id}/content` streams the file. Rendering takes minutes, so poll every 10 to 20 seconds rather than continuously; `GET /v1/videos` lists your recent jobs if you lose an id.

A job's estimated cost is held against your balance when it starts and settled to the actual cost when it finishes; a `failed` job is not charged. Download URLs are valid for 24 hours. Send an `Idempotency-Key` with the `POST` so a retry after a timeout cannot start a second job (see below).

## Embeddings

(code sample: https://docs.oceantoken.ai/api)

## Speech, transcription, rerank

`/v1/audio/speech` takes `model`, `input` text and a `voice` and returns audio bytes. `/v1/audio/transcriptions` takes a multipart upload with `model` and `file` and returns text. `/v1/rerank` takes a `query` and `documents` and returns them scored. Speech and transcription follow the OpenAI request shape, rerank the Cohere one; the model's page in the console shows an example for each.

## Retries and idempotency

Retry on `429`, `5xx` and network failures with backoff; never on other `4xx`. On the endpoints that cost money to run - `/v1/images/generations`, `/v1/images/edits`, `/v1/videos` and `/v1/audio/speech` - send an **`Idempotency-Key`** header so a retry replays the first answer instead of running again:

(code sample: https://docs.oceantoken.ai/api)

The rules (24-hour window, `409` on reuse with a different body, `Retry-After` while the first call runs) are in [Errors](https://docs.oceantoken.ai/errors#retrying-a-request-that-costs-money).

## What a request cost

Every successful response includes `usage`, and every request appears in the console under **Logs** with what it was charged. To read the cost from code:

- **A non-streaming response** carries it in the header **`x-oceantoken-cost`**, in US dollars, rounded to four significant figures. Your balance is charged the exact amount.
- **A streamed chat completion** cannot: headers are sent before the first token, and the cost is known only after the last. Look it up afterwards with `GET /v1/usage/{request_id}`, where `request_id` is the `id` of the completion. Every chunk of a stream carries it.

```bash
curl https://api.oceantoken.ai/v1/usage/$REQUEST_ID \
  -H "Authorization: Bearer $OCEANTOKEN_API_KEY"
```

The answer has `id`, `model`, `cost` (US dollars, four significant figures), `status`, `usage` with `prompt_tokens`, `completion_tokens` and `total_tokens`, `started_at`, `ended_at` and `duration_ms`.

- Use the key that made the request. With any other key the answer is `404`, so the endpoint never confirms that someone else's request exists.
- The cost is recorded a few seconds after the request finishes, and until then the answer is also `404`. Retry after a few seconds.
- The lookup takes the `id` in the response body, not the `x-oceantoken-request-id` header described in [Errors](https://docs.oceantoken.ai/errors#the-request-id).

Errors are described in [Errors](https://docs.oceantoken.ai/errors).

## Errors

Source: https://docs.oceantoken.ai/errors

Every failure is a JSON body with an HTTP status. This is the answer to a request sent without a key:

```json
{
  "error": {
    "message": "Missing API key. Send it as: Authorization: Bearer <your OceanToken key>.",
    "type": "authentication_error",
    "param": null,
    "code": "invalid_api_key"
  }
}
```

Branch on **`code`**. It is a fixed vocabulary that we keep stable; `message` is for people and its wording may change. `type` groups codes into families that are handled the same way. The HTTP status tells you the same thing at a coarser grain, so existing clients that branch on it keep working.

## Codes

| HTTP | `type` | `code` | What happened | What to do |
|---|---|---|---|---|
| 400 | `invalid_request_error` | `invalid_request` | The request was malformed: a missing field, a value the model does not accept, a bad image. | Fix the request. Do not retry as-is. |
| 400 | `not_found_error` | `model_not_found` | The `model` name does not exist. | Pick a name from `GET /v1/models`. |
| 400 | `insufficient_credits` | `insufficient_credits` | Your available credits are exhausted. Nothing ran and nothing was charged. | [Add credits](https://docs.oceantoken.ai/get-started/add-credits), then retry. |
| 400 | `insufficient_credits` | `key_budget_exceeded` | This key's own credit limit is used up (your account may still have credits). | Raise the key's limit, wait for its reset, or use another key. |
| 400 | `content_policy_violation` | `content_filtered` | A safety check refused the request before the model ran. Not charged. | Change the input. Retrying the same input gives the same answer. |
| 401 | `authentication_error` | `invalid_api_key` | No key, an unknown key, or a deleted key. | Check the `Authorization: Bearer sk-...` header. |
| 401 | `authentication_error` | `key_expired` | The key's expiration date has passed. | Create a new key. |
| 403 | `permission_error` | `model_not_allowed` | The key is valid but this model is outside your account's allowed set. | Use a model from `GET /v1/models`. |
| 403 | `permission_error` | `forbidden` | The key may not perform this operation. Managing API keys is one: an API key cannot create, change, rotate or delete keys. | Manage keys in the [console](https://docs.oceantoken.ai/console/api-keys); otherwise use a key with the right scope. |
| 404 | `not_found_error` | `not_found` | Unknown path, or a video / job id that does not exist. | Check the URL and the id. |
| 409 | `idempotency_error` | `idempotency_key_reused` | The `Idempotency-Key` was already used with a different body. | Use a fresh key for a new request. See [Retries](#retries). |
| 409 | `idempotency_error` | `idempotency_key_in_progress` | The first request with this key is still running. | Wait for `Retry-After` seconds, then retry the same request. |
| 429 | `rate_limit_error` | `rate_limited` | You exceeded your key's requests- or tokens-per-minute limit. | Back off until `Retry-After`; see [Limits](https://docs.oceantoken.ai/limits). |
| 429 | `rate_limit_error` | `provider_overloaded` | Every channel of the model is at capacity right now. See [Retries and failover](https://docs.oceantoken.ai/reliability). | Retry with backoff, or switch models. |
| 5xx | `api_error` | `provider_error` | The model failed, after the gateway's own retry and failover. Not charged. | Retry with backoff; if it persists, switch models. |
| 408 | `api_error` | `timeout` | A stream received nothing from the model for 120 seconds after it started. | Retry with backoff. |
| 504 | `api_error` | `timeout` | The request ran past the [240-second window](https://docs.oceantoken.ai/limits#timeouts). | Stream the response, shorten the request, or use an asynchronous endpoint. |

Anything not in this table is an `api_error`. New codes may be added; existing ones are not renamed or removed.

## The request ID

Responses to model requests carry the header **`x-oceantoken-request-id`**. Log it with your errors and quote it when you write to us. A request refused for its key (`401`) never reached a model and has none.

A successful response also has an `id` in its body, and every chunk of a stream carries the same `id`. That is the **Request ID** the console shows under **Logs**, with the request's status, latency and cost, and the id that [`GET /v1/usage/{request_id}`](https://docs.oceantoken.ai/api#what-a-request-cost) looks up.

## Retries

Before an error reaches you, the gateway has already retried it and, where the model has another channel, moved the request there. [Retries and failover](https://docs.oceantoken.ai/reliability) explains what it handles and what it leaves to you.

Retry **only** on `429`, `5xx`, a `timeout` error and network failures (a dropped connection, a client-side timeout). Everything in the 400 range will fail the same way again until the request or the account changes.

Use exponential backoff with jitter, starting around one second and capping at about thirty; when the response carries `Retry-After` (a number of seconds), wait at least that long.

(code sample: https://docs.oceantoken.ai/errors)

### Retrying a request that costs money

Image, video and speech requests are charged when they run. A retry after a network timeout would otherwise run them a second time. Send an **`Idempotency-Key`** header (any unique string, up to 255 characters, for example a UUID) on `POST /v1/images/generations`, `/v1/images/edits`, `/v1/videos` and `/v1/audio/speech`:

- The first request runs normally and its response is kept for **24 hours**.
- A retry with the same key **and the same body** gets that response back, marked with the header `Idempotency-Replayed: true`. Nothing runs and nothing is charged.
- The same key with a **different body** is refused with `409 idempotency_key_reused`.
- A retry while the first request is **still running** gets `409 idempotency_key_in_progress` with `Retry-After`.
- A `5xx` answer is not kept, so a retry after a provider failure runs again.

Keys are scoped to your API key. The header is ignored on every other endpoint, and on the endpoints above a request without it behaves exactly as before. Responses above 8 MB are not kept; the request still runs, only the replay does not apply.

## Errors while streaming

With `"stream": true`, an error that occurs before the first token is an ordinary JSON error response with the status above. An error after the stream has started arrives as a final `data:` chunk whose payload is the same `error` object, and then the stream ends.

A stream that ends early, because the connection broke, you disconnected, or an error cut it off, is billed at the model's usual prices for:

- its **prompt**, in full;
- the **output streamed up to that point**. A reasoning model's streamed reasoning counts as output, even when no answer text had arrived yet.

Output the model may have gone on generating after the stream stopped is not billed. A stream that ended before producing any output is not billed at all.

## Balance exhausted

When your balance is at or below $0, every request is refused with `400 insufficient_credits`, free models included. Nothing is run and nothing is charged. [Add credits](https://docs.oceantoken.ai/get-started/add-credits) and retry.

## Content policy

Requests that trip a safety check are refused with `400 content_filtered`. The check runs before the model is called, so the request is not charged.

## Finding a failed request

Every failure is recorded in the console under **Logs** with its status and the response body. Find it by its time and model, and quote its `x-oceantoken-request-id` when you write to us.

## Frequently asked questions

Source: https://docs.oceantoken.ai/faq

Short answers, each complete on its own. For the exact value to send as `model`, and today's price, use the [Models](https://docs.oceantoken.ai/models) page.

### What is OceanToken?

OceanToken is one API and one prepaid balance for nearly 500 AI models: text, image, video, speech, transcription, embedding and rerank models from OpenAI, Anthropic, Google, DeepSeek, Qwen, ByteDance and about 60 other publishers. You create one account, add credits, create an API key, and call any model with the same base URL and the same key. Every model's price, context window and capabilities are listed in the catalog before you call it.

### Is OceanToken OpenAI-compatible? Which SDKs work?

Yes. The OceanToken API speaks the OpenAI API, so the official OpenAI SDKs for Python, TypeScript and other languages work after changing two values: the base URL to https://api.oceantoken.ai/v1 and the API key to your OceanToken key. Claude models also answer on the Anthropic Messages API at /v1/messages, so the Anthropic SDK works unchanged with the same two changes; it takes the base URL https://api.oceantoken.ai and adds /v1 itself. Chat completions, the Responses API, images, video, embeddings, speech, transcription and rerank all follow the same shapes.

### Which AI models can I call through OceanToken?

The catalog holds nearly 500 models across 7 types: language models (GPT, Claude, Gemini, DeepSeek, Qwen, GLM, Kimi, Grok, Mistral, Llama and more), image generation and editing models, video generation models, text-to-speech, speech-to-text, text embeddings and rerankers. The Models page lists every one with its exact model ID, price per unit, context window and whether it supports reasoning, tool calling or image input. The list is rebuilt from the live service every time the documentation is published.

### How much does OceanToken cost? Is there a platform fee?

You pay per use at the price shown for each model, in US dollars, from a prepaid balance; there is no subscription and no platform fee on top of the model price. Language models are priced per 1 million input, cached input and output tokens (and cache writes, where a model charges for them); images per image, per megapixel or per image token; video per second; speech per 1,000 characters; transcription per minute of audio; and Cohere rerank per search unit. A model's price is the same at every hour of the day, and smart-router is billed at the price of the model it picks. Some models are tagged :free and cost nothing with limited throughput. Each model page shows the current price before you make a call.

### How do I use OceanToken with Claude Code, Codex, Cursor or Gemini CLI?

Run one command in a terminal and sign in: npx -y @oceantoken/cli@latest connect codex (or claude-code, cursor, gemini, openclaw). It adds the OceanToken MCP server at https://mcp.oceantoken.ai/mcp and 3 skills to that agent, which can then search models, estimate costs and generate images, video and speech from your balance. An AI agent can also follow the instructions at https://mcp.oceantoken.ai/install on its own. The same API key works in any OpenAI-compatible tool by setting the base URL.

### Does OceanToken generate images, video and speech, not just text?

Yes. Image models answer on /v1/images/generations and /v1/images/edits, video models on /v1/videos as asynchronous jobs you poll, text-to-speech on /v1/audio/speech, transcription on /v1/audio/transcriptions, embeddings on /v1/embeddings and rerankers on /v1/rerank. All 7 types use the same key and balance, and each request appears in the console's Logs with its cost and latency. Image and video download URLs stay valid for 24 hours, and video jobs accept an Idempotency-Key so a retry can never start and bill a second job.

### Can I limit how much an API key can spend?

Yes. Each API key can carry its own credit limit, optionally resetting daily, weekly or monthly, plus an expiry date, so a key for a test project or a teammate cannot draw more than you allow from the shared balance; a key that has used its limit gets a 400 key_budget_exceeded error while the account may still have credits. The console shows every key's usage, and the Logs page lists each request with its model, tokens, cost and latency. Keys are shown once at creation and can be rotated with a 24-hour overlap.

### How does billing and the prepaid balance work?

You add credits by card in the console, between $10 and $100,000 at a time, and every request deducts its exact cost from that prepaid balance at the price listed for the model when the call is made, never retroactively. Purchased credits are valid for 12 months from purchase (Terms of Service, section 6), and there is no monthly minimum. While the balance is at or below $0 every request is refused, free models included, until you add credits, and long jobs such as video hold their estimated cost until they finish. Spend shows per day and per model on the Activity page.

### Is there a free tier on OceanToken?

Models whose ID ends in :free cost nothing to call, with limited and unguaranteed throughput; the Models page filters show them with a Free label. Like every model they can be called only while your balance is above $0, but calls to them do not reduce it, so after a first top-up you can test the API shape, SDK setup and agent integration without spending, then switch to a paid model by changing only the model ID.

### What are OceanToken's rate limits and timeouts?

Rate limits are per API key, as requests per minute and tokens per minute, and responses carry the key's limits in the x-oceantoken-key-rpm-limit and x-oceantoken-key-tpm-limit headers; exceeding one returns 429 rate_limited with a Retry-After header. A synchronous request may run for at most 240 seconds and a request body may be at most 10 MB, so long text generations should use stream: true and large files should be sent as URLs. Video generation runs as a job that takes minutes, so you poll /v1/videos/{video_id} instead of holding a connection open. Details are on the Limits page.

### What happens if a model provider goes down?

Usually nothing you can see. Many models, including the current Claude and GPT models, have more than one official or authorized channel; when one fails, is at capacity or goes quiet, OceanToken retries the request and moves it to another channel of the same model, at the same price. It never answers with a different model unless you name backup models yourself with the fallbacks parameter, and an attempt that fails before producing output is not billed. Errors that any channel would return, such as a malformed request or a safety refusal, come back to you directly, and a stream that breaks after output has started can end with an error, so keep a retry with backoff for 429 and 5xx. The Retries and failover page has the details.


## Limits

Source: https://docs.oceantoken.ai/limits

## Spending

Your balance is the hard limit: while it is at or below $0, every request is refused with `400 insufficient_credits` before it runs, free models included. A request is charged when it finishes, so the one that uses up the last of the balance can take it below $0; the next one is refused until you add credits. Each key can carry its own **credit limit**, optionally resetting daily, weekly or monthly, and an **expiration**; a key that has used its limit gets `400 key_budget_exceeded` while the account may still have credits. See [Create an API key](https://docs.oceantoken.ai/get-started/create-api-key).

Video jobs and deep research hold their **estimated** cost against your balance when they start and settle to the actual cost when they finish; a failed job releases the hold.

## Rate limits

Rate limits are **per key**, as requests per minute and tokens per minute, and are set by us for your account. Responses carry the key's limits, so a client can pace itself:

| Header | Meaning |
|---|---|
| `x-oceantoken-key-rpm-limit` | Requests allowed per minute on this key |
| `x-oceantoken-key-tpm-limit` | Tokens allowed per minute on this key |
| `x-oceantoken-key-spend` / `x-oceantoken-key-budget` | What this key has spent, and its credit limit |

Exceeding either rate returns `429 rate_limited` with a `Retry-After` header giving the seconds until the minute window resets. A header whose limit is not set on the key is left out.

Separately, each model's channels have their own capacity. When one is busy the gateway moves the request to another channel of the same model, if it has one ([Retries and failover](https://docs.oceantoken.ai/reliability)). When every channel of a model is busy you get `429 provider_overloaded`; that is the moment to retry with backoff or switch models. If your application needs sustained throughput beyond what your key allows, contact us and we will raise it.

## Request size

The whole request, JSON or multipart, may be at most **10 MB**. That is a gateway limit and cannot be raised per account. For images and audio, send a URL or upload the file where the endpoint allows it rather than embedding a large base64 payload.

## Timeouts

A synchronous request is held open for at most **240 seconds**, measured from the start of the request to the last byte of the response. Past that the connection is closed and the client sees `504 timeout`. Long text generations should use `"stream": true`; a stream stays open as long as tokens keep flowing. Video generation is a job you poll, so it is never affected.

## Retention

| What | Kept for |
|---|---|
| Image and video download URLs in API responses | **24 hours**. Download the file promptly; the URL is not a permanent address. |
| A stored `Idempotency-Key` response | 24 hours |
| Request content: the prompts and responses of your requests | **365 days** after the request, then deleted automatically. You can ask for it to be deleted sooner by writing to support@oceantoken.ai |
| Files you upload, and images, audio and video generated for you | **30 days** after upload or generation, then deleted automatically. A saved conversation keeps its text, but images and files in it older than 30 days no longer display. |
| Usage and billing records: each request's model, token counts, cost and time | While your account is open, and afterwards for as long as legally or commercially reasonably required. Deleting request content does not delete them; your balance and invoices are built from them |
| Saved chat conversations in the console | **365 days** after they were last updated, then deleted automatically. You can delete one yourself at any time |

The console has no setting to change these periods or where requests are processed. These periods are the ones the [privacy policy](https://app.oceantoken.ai/legal/privacy) states; it is the full statement of what is stored, who processes it and where, and how to have your records deleted when you close your account.

## Model access

An account can be limited to a set of models. `GET /v1/models` lists what your key can call; anything outside it returns `403 model_not_allowed`. The console's Models page shows the same set.

## Models and prices

Source: https://docs.oceantoken.ai/models

Every model you can call through the OceanToken API, with its price in the unit you are billed in. The name in the first column is the exact `model` value to send, and links to that model's own page with its context window, capabilities, a ready-to-run request and the closest alternatives. The prices are read from the same live catalog as the console's **Models** page, on the date shown above the table, when these docs were built. If a model or price has changed since, the console shows the current one.

(the model table: https://docs.oceantoken.ai/models; every model also has its own page)

## How prices are shown

| Unit | Meaning |
|---|---|
| `/ 1M tokens` | Per million tokens. **Input**, **Cached input** (prompt tokens read from the cache), **Cache write** (prompt tokens written into the cache, on models that charge for it; **1 h** is the price of a one-hour cache) and **Output** are priced separately. An image model priced this way shows its generated image tokens as **Output** |
| `/ image` | Per generated image |
| `/ megapixel` | Image: per megapixel of output. **first MP, then $x / MP** means the first megapixel of each image costs the listed price and each further megapixel costs $x. A price under **Input** is per megapixel of the images you send |
| `/ search unit` | Rerank: per search unit, as counted in the response's `meta.billed_units.search_units` |
| `/ 1K chars` | Speech: per thousand characters of input text |
| `/ min` | Transcription: per minute of audio |
| `from … / s` | Video: per second of output, starting from the lowest resolution and mode |
| **Free · rate-limited** | No charge; throughput is limited and not guaranteed. Like every model, it can be called only while your balance is above $0 |
| **Price TBD** | Callable now. Its price has not been published yet, so calls are free until it is; the price applies from the moment it appears here, never retroactively |

## How you are charged

- **Text models** are charged tokens times the prices in this table: input, cached input, cache writes where a **Cache write** price is shown, and output. Some models charge more once a prompt passes a length threshold, which the table does not show. A request that uses web search is charged its actual cost, searches included.
- **One price all day.** A model's price does not change with the time of day: the price in this table applies at every hour.
- **Image, video, speech, transcription, embedding and rerank models** are charged the actual cost of each request. The price shown is the rate for a typical request; what you pay depends on what you ask for, such as size, quality, resolution, duration, or the length of the text or audio.
- **`smart-router`** has no price of its own. It picks a text model for each request, and the request is billed at that model's listed price, with nothing added for the routing. **Logs** shows which model answered.

Every request's charge is in the console under **Logs**, and a non-streaming response carries it in the `x-oceantoken-cost` header; see [What a request cost](https://docs.oceantoken.ai/api#what-a-request-cost). Prices are in US dollars. There are no platform fees on top.

## Which endpoint

| Type | Endpoint |
|---|---|
| Text | `/v1/chat/completions`, `/v1/responses`, or `/v1/messages` for Claude |
| Image | `/v1/images/generations`, `/v1/images/edits` |
| Video | `/v1/videos` |
| Embeddings | `/v1/embeddings` |
| Speech | `/v1/audio/speech` |
| Transcription | `/v1/audio/transcriptions` |
| Rerank | `/v1/rerank` |

## Your key's list

`GET /v1/models` returns the models your key can call. If your account has been limited to a set of models, only those appear there and in the console; anything else returns an error.

## Retries and automatic failover

Source: https://docs.oceantoken.ai/reliability

Many models on OceanToken have more than one channel, and every channel is an official or authorized source of the same model. When one fails, the gateway retries the request and, if the model has another channel, moves the request there. You get the answer from the model you asked for, at the same price, a little later. Most of the time you will not see the failure at all.

This page explains what happens in each case and which errors still reach your code.

## How a request is served

- **Failover never changes the model.** A request for a model is answered by that model, whichever channel serves it. A different model is tried only if you ask for one with [`fallbacks`](#your-own-backup-models).
- **Channels are ranked.** The first healthy channel serves the request; the next one takes over when it fails.
- **Coverage.** The models with more than one channel include the current Claude and GPT models and several image and video models. Other models have a single channel today: they still get one retry after a temporary error, but there is nowhere to switch to.
- **The channel does not change the result.** The model, the price and the response format are the same whichever channel answers. The response does not say which channel answered.

## When a channel fails

| What happens upstream | What the gateway does | What you see |
|---|---|---|
| A temporary error: a server error, a dropped connection, a timeout on that channel | Retries once on the same channel, then moves to the next channel | A normal response, a little later |
| The channel is at capacity (it answers "too many requests") | Moves straight to the next channel, without retrying the busy one | A normal response |
| A channel keeps failing | Takes it out of rotation for a short time, so the next requests go straight to a working channel | Nothing |
| Every channel has failed | Returns the last error | `5xx provider_error`, or `429 provider_overloaded` when every channel is at capacity. Nothing is charged. |

You do not need to retry the failures the gateway handles for you. Keep a retry in your client for the errors that do reach it: `429` and `5xx` with exponential backoff, as shown in [Errors → Retries](https://docs.oceantoken.ai/errors#retries).

## What is not retried

Some failures would happen on every channel, so moving the request does not help. These come back to you as errors:

| Failure | Code | What to do |
|---|---|---|
| The request itself is wrong: a missing field, a value the model does not accept, a prompt longer than the model's context window | `400 invalid_request` | Fix the request. |
| A safety check refused the request or the answer | `400 content_filtered` | Change the input. A refusal is never sent on to another channel. |
| Your key, account or balance: an unknown model, a model outside your account, an invalid or expired key, no credits left, the key's own limit reached | `400`, `401`, `403`, see [Errors](https://docs.oceantoken.ai/errors#codes) | Fix the key or the account. |
| Your key's own rate limit | `429 rate_limited` | Wait for `Retry-After`. See [Limits](https://docs.oceantoken.ai/limits#rate-limits). |

**A channel that goes quiet is abandoned.** On a streamed request, if a channel sends nothing for 120 seconds before the first token, the request moves to the next channel. A non-streamed request still running after 240 seconds is closed with `504 timeout` ([Limits → Timeouts](https://docs.oceantoken.ai/limits#timeouts)). For long answers, stream.

## Streaming

- **Before the first token**, failover works exactly as above. The stream starts a little later.
- **After the answer has started**, a clean switch is not guaranteed. Depending on the endpoint, the gateway either finishes the answer on another channel or ends the stream with an error event, as described in [Errors → Errors while streaming](https://docs.oceantoken.ai/errors#errors-while-streaming).

Check that every stream ends with a finish reason: `finish_reason` on Chat Completions, `stop_reason` on Messages, a `response.completed` event on Responses. A stream without one is incomplete; retry it.

## Video jobs

Failover happens when a job is submitted. If the first channel refuses or fails the submission, the next channel takes it. Once a job has been accepted, it runs to the end on that channel. If it fails, it is reported as failed and its hold on your balance is released ([Limits → Spending](https://docs.oceantoken.ai/limits#spending)). To retry a submission safely after a network error, send an `Idempotency-Key` ([Errors → Retrying a request that costs money](https://docs.oceantoken.ai/errors#retrying-a-request-that-costs-money)).

## Billing

- **You pay the model's listed price, whichever channel answers.** The price on the [Models](https://docs.oceantoken.ai/models) page applies to every channel.
- **Retries and switches are free.** An attempt that fails before the model has produced any output is not billed; you pay for the answer you get. A stream that breaks after output has started is billed for its prompt and for the output streamed up to that point, reasoning included, and for nothing generated after it stopped ([Errors → Errors while streaming](https://docs.oceantoken.ai/errors#errors-while-streaming)).
- **Prompt caching does not carry over.** Cached input is kept per channel. The first request served by a different channel may bill input at the regular rate where it would otherwise have been a cache hit.

## Your own backup models

You can also name other models to try if the model you asked for fails on all of its channels. Add `fallbacks` to the request body, as a list of model names in the order to try them. It works on `/v1/chat/completions` and `/v1/responses`.

  
    (code sample: https://docs.oceantoken.ai/reliability)
  
  
    (code sample: https://docs.oceantoken.ai/reliability)
  

- Your backup models are tried after every channel of the requested model has failed. Unlike the gateway's own failover, they are tried for any error the model returns, including a prompt that is too long for its context window.
- Errors about your key, account, balance or rate limit, and refusals by OceanToken's own safety checks, are returned without trying them.
- Every name must be a model your key can call. An unknown name is refused with `400 model_not_found` before anything runs.
- **You are billed at the price of the model that answered.** The `x-oceantoken-model` response header names it, and so does `model` in a non-streaming response.

## Recommended client settings

- Retry `429` and `5xx` with exponential backoff and jitter, and honour `Retry-After` ([Errors → Retries](https://docs.oceantoken.ai/errors#retries)).
- Let a non-streaming request run for the full 240 seconds before your client gives up, or stream.
- Send an `Idempotency-Key` on image, video and speech requests, so a retry never runs and bills twice.
- Log the `x-oceantoken-request-id` header. It finds the request in the console under **Logs**, and it is what to quote when you write to us.

## If errors persist

Failures are retried and moved automatically as described above. If a model keeps returning errors after your own retries, write to support@oceantoken.ai with the `x-oceantoken-request-id` of a few failed requests.

## Models (483)

Every model callable through the OceanToken API, with its price in the unit you are billed in. The model ID is the exact value to send as `model`. Full table: https://docs.oceantoken.ai/models.

## Aion Labs models

Index: https://docs.oceantoken.ai/models/aion-labs

### Aion 2.0 (`aion-labs/aion-2.0`)

aion-labs/aion-2.0 is a language model from Aion Labs you can call on the OceanToken API at $0.80 per 1M input tokens and $1.60 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: aion-labs/aion-2.0
- Type: Text
- Publisher: Aion Labs
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $0.80 per 1M tokens
- Output price: $1.60 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-23
- Page: https://docs.oceantoken.ai/models/aion-labs/aion-2.0

### Aion 3.0 (`aion-labs/aion-3.0`)

aion-labs/aion-3.0 is a language model from Aion Labs you can call on the OceanToken API at $3.00 per 1M input tokens and $6.00 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: aion-labs/aion-3.0
- Type: Text
- Publisher: Aion Labs
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $3.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.75 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-07
- Page: https://docs.oceantoken.ai/models/aion-labs/aion-3.0

### Aion 3.0 Mini (`aion-labs/aion-3.0-mini`)

aion-labs/aion-3.0-mini is a language model from Aion Labs you can call on the OceanToken API at $0.70 per 1M input tokens and $1.40 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: aion-labs/aion-3.0-mini
- Type: Text
- Publisher: Aion Labs
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $0.70 per 1M tokens
- Output price: $1.40 per 1M tokens
- Cached input price: $0.18 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-07
- Page: https://docs.oceantoken.ai/models/aion-labs/aion-3.0-mini

### Aion RP Llama 3.1 8B (`aion-labs/aion-rp-llama-3.1-8b`)

aion-labs/aion-rp-llama-3.1-8b is a language model from Aion Labs you can call on the OceanToken API at $0.80 per 1M input tokens and $1.60 per 1M output tokens, with a 33K-token context window and up to 29K output tokens.

- Model ID: aion-labs/aion-rp-llama-3.1-8b
- Type: Text
- Publisher: Aion Labs
- Context window: 32,768 tokens
- Max output: 29,491 tokens
- Input price: $0.80 per 1M tokens
- Output price: $1.60 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-02-04
- Page: https://docs.oceantoken.ai/models/aion-labs/aion-rp-llama-3.1-8b

## Alibaba models

Index: https://docs.oceantoken.ai/models/alibaba

### Happyhorse 1.0 (`alibaba/happyhorse-1.0`)

alibaba/happyhorse-1.0 is a video generation model from Alibaba you can call on the OceanToken API at from $0.0988 per second of generated video.

- Model ID: alibaba/happyhorse-1.0
- Type: Video
- Publisher: Alibaba
- Price: from $0.0988 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-24
- Page: https://docs.oceantoken.ai/models/alibaba/happyhorse-1.0

### Happyhorse 1.1 (`alibaba/happyhorse-1.1`)

alibaba/happyhorse-1.1 is a video generation model from Alibaba you can call on the OceanToken API at from $0.0988 per second of generated video.

- Model ID: alibaba/happyhorse-1.1
- Type: Video
- Publisher: Alibaba
- Price: from $0.0988 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-24
- Page: https://docs.oceantoken.ai/models/alibaba/happyhorse-1.1

### Wan 2.6 (`alibaba/wan-2.6`)

alibaba/wan-2.6 is a video generation model from Alibaba you can call on the OceanToken API at from $0.04 per second of generated video.

- Model ID: alibaba/wan-2.6
- Type: Video
- Publisher: Alibaba
- Price: from $0.04 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-28
- Page: https://docs.oceantoken.ai/models/alibaba/wan-2.6

### Wan 2.7 (`alibaba/wan-2.7`)

alibaba/wan-2.7 is a video generation model from Alibaba you can call on the OceanToken API at from $0.10 per second of generated video.

- Model ID: alibaba/wan-2.7
- Type: Video
- Publisher: Alibaba
- Price: from $0.10 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-15
- Page: https://docs.oceantoken.ai/models/alibaba/wan-2.7

### Wan 3.0 (`alibaba/wan-3.0`)

alibaba/wan-3.0 is a video generation model from Alibaba you can call on the OceanToken API at from $0.05 per second of generated video.

- Model ID: alibaba/wan-3.0
- Type: Video
- Publisher: Alibaba
- Price: from $0.05 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-24
- Page: https://docs.oceantoken.ai/models/alibaba/wan-3.0

### Wan 3.0 Prime (`alibaba/wan-3.0-prime`)

alibaba/wan-3.0-prime is a video generation model from Alibaba you can call on the OceanToken API at from $0.068 per second of generated video.

- Model ID: alibaba/wan-3.0-prime
- Type: Video
- Publisher: Alibaba
- Price: from $0.068 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-27
- Page: https://docs.oceantoken.ai/models/alibaba/wan-3.0-prime

## Amazon models

Index: https://docs.oceantoken.ai/models/amazon

### Nova 2 Lite V1 (`amazon/nova-2-lite-v1`)

amazon/nova-2-lite-v1 is a language model from Amazon you can call on the OceanToken API at $0.30 per 1M input tokens and $2.50 per 1M output tokens, with a 1M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: amazon/nova-2-lite-v1
- Type: Text
- Publisher: Amazon
- Context window: 1,000,000 tokens
- Max output: 65,535 tokens
- Input price: $0.30 per 1M tokens
- Output price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-02
- Page: https://docs.oceantoken.ai/models/amazon/nova-2-lite-v1

### Nova Lite V1 (`amazon/nova-lite-v1`)

amazon/nova-lite-v1 is a language model from Amazon you can call on the OceanToken API at $0.06 per 1M input tokens and $0.24 per 1M output tokens, with a 300K-token context window and up to 5K output tokens; it supports tool calling, image input.

- Model ID: amazon/nova-lite-v1
- Type: Text
- Publisher: Amazon
- Context window: 300,000 tokens
- Max output: 5,120 tokens
- Input price: $0.06 per 1M tokens
- Output price: $0.24 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-05
- Page: https://docs.oceantoken.ai/models/amazon/nova-lite-v1

### Nova Micro V1 (`amazon/nova-micro-v1`)

amazon/nova-micro-v1 is a language model from Amazon you can call on the OceanToken API at $0.035 per 1M input tokens and $0.14 per 1M output tokens, with a 128K-token context window and up to 5K output tokens; it supports tool calling.

- Model ID: amazon/nova-micro-v1
- Type: Text
- Publisher: Amazon
- Context window: 128,000 tokens
- Max output: 5,120 tokens
- Input price: $0.035 per 1M tokens
- Output price: $0.14 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-05
- Page: https://docs.oceantoken.ai/models/amazon/nova-micro-v1

### Nova Pro V1 (`amazon/nova-pro-v1`)

amazon/nova-pro-v1 is a language model from Amazon you can call on the OceanToken API at $0.80 per 1M input tokens and $3.20 per 1M output tokens, with a 300K-token context window and up to 5K output tokens; it supports tool calling, image input.

- Model ID: amazon/nova-pro-v1
- Type: Text
- Publisher: Amazon
- Context window: 300,000 tokens
- Max output: 5,120 tokens
- Input price: $0.80 per 1M tokens
- Output price: $3.20 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-05
- Page: https://docs.oceantoken.ai/models/amazon/nova-pro-v1

## Anthracite models

Index: https://docs.oceantoken.ai/models/anthracite-org

### Magnum V4 72B (`anthracite-org/magnum-v4-72b`)

anthracite-org/magnum-v4-72b is a language model from Anthracite you can call on the OceanToken API at $2.50 per 1M input tokens and $5.00 per 1M output tokens, with a 33K-token context window and up to 4K output tokens.

- Model ID: anthracite-org/magnum-v4-72b
- Type: Text
- Publisher: Anthracite
- Context window: 32,768 tokens
- Max output: 4,096 tokens
- Input price: $2.50 per 1M tokens
- Output price: $5.00 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-10-22
- Page: https://docs.oceantoken.ai/models/anthracite-org/magnum-v4-72b

## Anthropic models

Index: https://docs.oceantoken.ai/models/anthropic

### Claude Fable 5 (`anthropic/claude-fable-5`)

anthropic/claude-fable-5 is a language model from Anthropic you can call on the OceanToken API at $10.00 per 1M input tokens and $50.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-fable-5
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $10.00 per 1M tokens
- Output price: $50.00 per 1M tokens
- Cached input price: $1.00 per 1M tokens
- Cache write price: $12.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-06-09
- Page: https://docs.oceantoken.ai/models/anthropic/claude-fable-5

### Claude Fable 5.1 (`anthropic/claude-fable-5.1`)

anthropic/claude-fable-5.1 is a language model from Anthropic you can call on the OceanToken API at $10.00 per 1M input tokens and $50.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-fable-5.1
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $10.00 per 1M tokens
- Output price: $50.00 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Cache write price: $12.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-09-01
- Page: https://docs.oceantoken.ai/models/anthropic/claude-fable-5.1

### Claude Fable Latest (`anthropic/claude-fable-latest`)

anthropic/claude-fable-latest is a language model from Anthropic you can call on the OceanToken API at $10.00 per 1M input tokens and $50.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-fable-latest
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $10.00 per 1M tokens
- Output price: $50.00 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Cache write price: $12.50 per 1M tokens (1-hour cache: $20.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- Alias of: anthropic/claude-fable-5.1
- In the catalog since: 2026-06-09
- Page: https://docs.oceantoken.ai/models/anthropic/claude-fable-latest

### Claude Haiku 4.5 (`anthropic/claude-haiku-4.5`)

anthropic/claude-haiku-4.5 is a language model from Anthropic you can call on the OceanToken API at $1.00 per 1M input tokens and $5.00 per 1M output tokens, with a 200K-token context window and up to 64K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-haiku-4.5
- Type: Text
- Publisher: Anthropic
- Context window: 200,000 tokens
- Max output: 64,000 tokens
- Input price: $1.00 per 1M tokens
- Output price: $5.00 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Cache write price: $1.25 per 1M tokens (1-hour cache: $2.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2025-10-15
- Page: https://docs.oceantoken.ai/models/anthropic/claude-haiku-4.5

### Claude Haiku Latest (`anthropic/claude-haiku-latest`)

anthropic/claude-haiku-latest is a language model from Anthropic you can call on the OceanToken API at $0.10 per 1M input tokens and $0.50 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-haiku-latest
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.50 per 1M tokens
- Cached input price: $0.01 per 1M tokens
- Cache write price: $0.125 per 1M tokens (1-hour cache: $0.20)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- Alias of: anthropic/claude-haiku-5.5
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/anthropic/claude-haiku-latest

### Claude Opus 4.1 (`anthropic/claude-opus-4.1`)

anthropic/claude-opus-4.1 is a language model from Anthropic you can call on the OceanToken API at $15.00 per 1M input tokens and $75.00 per 1M output tokens, with a 200K-token context window and up to 32K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-4.1
- Type: Text
- Publisher: Anthropic
- Context window: 200,000 tokens
- Max output: 32,000 tokens
- Input price: $15.00 per 1M tokens
- Output price: $75.00 per 1M tokens
- Cached input price: $1.50 per 1M tokens
- Cache write price: $18.75 per 1M tokens (1-hour cache: $30.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2025-08-05
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-4.1

### Claude Opus 4.5 (`anthropic/claude-opus-4.5`)

anthropic/claude-opus-4.5 is a language model from Anthropic you can call on the OceanToken API at $5.00 per 1M input tokens and $25.00 per 1M output tokens, with a 200K-token context window and up to 64K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-4.5
- Type: Text
- Publisher: Anthropic
- Context window: 200,000 tokens
- Max output: 64,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $25.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Cache write price: $6.25 per 1M tokens (1-hour cache: $10.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2025-11-24
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-4.5

### Claude Opus 4.6 (`anthropic/claude-opus-4.6`)

anthropic/claude-opus-4.6 is a language model from Anthropic you can call on the OceanToken API at $5.00 per 1M input tokens and $25.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-4.6
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $25.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Cache write price: $6.25 per 1M tokens (1-hour cache: $10.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-02-04
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-4.6

### Claude Opus 4.7 (`anthropic/claude-opus-4.7`)

anthropic/claude-opus-4.7 is a language model from Anthropic you can call on the OceanToken API at $5.00 per 1M input tokens and $25.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-4.7
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $25.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Cache write price: $6.25 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-04-16
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-4.7

### Claude Opus 4.8 (`anthropic/claude-opus-4.8`)

anthropic/claude-opus-4.8 is a language model from Anthropic you can call on the OceanToken API at $5.00 per 1M input tokens and $25.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-4.8
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $25.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Cache write price: $6.25 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-05-27
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-4.8

### Claude Opus 5 (`anthropic/claude-opus-5`)

anthropic/claude-opus-5 is a language model from Anthropic you can call on the OceanToken API at $5.00 per 1M input tokens and $25.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-5
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $25.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Cache write price: $6.25 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-07-24
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-5

### Claude Opus 5.5 (`anthropic/claude-opus-5.5`)

anthropic/claude-opus-5.5 is a language model from Anthropic you can call on the OceanToken API at $4.00 per 1M input tokens and $20.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-5.5
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $4.00 per 1M tokens
- Output price: $20.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $5.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-09-22
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-5.5

### Claude Opus Latest (`anthropic/claude-opus-latest`)

anthropic/claude-opus-latest is a language model from Anthropic you can call on the OceanToken API at $4.00 per 1M input tokens and $20.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-opus-latest
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $4.00 per 1M tokens
- Output price: $20.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $5.00 per 1M tokens (1-hour cache: $8.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- Alias of: anthropic/claude-opus-5.5
- In the catalog since: 2026-04-21
- Page: https://docs.oceantoken.ai/models/anthropic/claude-opus-latest

### Claude Sonnet 4 (`anthropic/claude-sonnet-4`)

anthropic/claude-sonnet-4 is a language model from Anthropic you can call on the OceanToken API at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a 200K-token context window and up to 64K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-sonnet-4
- Type: Text
- Publisher: Anthropic
- Context window: 200,000 tokens
- Max output: 64,000 tokens
- Input price: $3.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Cached input price: $0.30 per 1M tokens
- Cache write price: $3.75 per 1M tokens (1-hour cache: $6.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2025-05-22
- Page: https://docs.oceantoken.ai/models/anthropic/claude-sonnet-4

### Claude Sonnet 4.5 (`anthropic/claude-sonnet-4.5`)

anthropic/claude-sonnet-4.5 is a language model from Anthropic you can call on the OceanToken API at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a 200K-token context window and up to 64K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-sonnet-4.5
- Type: Text
- Publisher: Anthropic
- Context window: 200,000 tokens
- Max output: 64,000 tokens
- Input price: $3.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Cached input price: $0.30 per 1M tokens
- Cache write price: $3.75 per 1M tokens (1-hour cache: $6.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2025-09-29
- Page: https://docs.oceantoken.ai/models/anthropic/claude-sonnet-4.5

### Claude Sonnet 4.6 (`anthropic/claude-sonnet-4.6`)

anthropic/claude-sonnet-4.6 is a language model from Anthropic you can call on the OceanToken API at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a 1M-token context window and up to 64K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-sonnet-4.6
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 64,000 tokens
- Input price: $3.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Cached input price: $0.30 per 1M tokens
- Cache write price: $3.75 per 1M tokens (1-hour cache: $6.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-02-17
- Page: https://docs.oceantoken.ai/models/anthropic/claude-sonnet-4.6

### Claude Sonnet 5 (`anthropic/claude-sonnet-5`)

anthropic/claude-sonnet-5 is a language model from Anthropic you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-sonnet-5
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-06-30
- Page: https://docs.oceantoken.ai/models/anthropic/claude-sonnet-5

### Claude Sonnet 5.5 (`anthropic/claude-sonnet-5.5`)

anthropic/claude-sonnet-5.5 is a language model from Anthropic you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-sonnet-5.5
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- In the catalog since: 2026-09-28
- Page: https://docs.oceantoken.ai/models/anthropic/claude-sonnet-5.5

### Claude Sonnet Latest (`anthropic/claude-sonnet-latest`)

anthropic/claude-sonnet-latest is a language model from Anthropic you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: anthropic/claude-sonnet-latest
- Type: Text
- Publisher: Anthropic
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Cache write price: $2.50 per 1M tokens (1-hour cache: $4.00)
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible, or Anthropic Messages (/v1/messages)
- Alias of: anthropic/claude-sonnet-5.5
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/anthropic/claude-sonnet-latest

## Arcee AI models

Index: https://docs.oceantoken.ai/models/arcee-ai

### Trinity Large Thinking (`arcee-ai/trinity-large-thinking`)

arcee-ai/trinity-large-thinking is a language model from Arcee AI you can call on the OceanToken API at $0.25 per 1M input tokens and $0.80 per 1M output tokens, with a 262K-token context window and up to 80K output tokens; it supports reasoning, tool calling.

- Model ID: arcee-ai/trinity-large-thinking
- Type: Text
- Publisher: Arcee AI
- Context window: 262,144 tokens
- Max output: 80,000 tokens
- Input price: $0.25 per 1M tokens
- Output price: $0.80 per 1M tokens
- Cached input price: $0.06 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-01
- Page: https://docs.oceantoken.ai/models/arcee-ai/trinity-large-thinking

## BAAI models

Index: https://docs.oceantoken.ai/models/baai

### BGE Base En V1.5 (`baai/bge-base-en-v1.5`)

baai/bge-base-en-v1.5 is a text embedding model from BAAI you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: baai/bge-base-en-v1.5
- Type: Embeddings
- Publisher: BAAI
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/baai/bge-base-en-v1.5

### BGE Large En V1.5 (`baai/bge-large-en-v1.5`)

baai/bge-large-en-v1.5 is a text embedding model from BAAI you can call on the OceanToken API at $0.01 per 1M input tokens, with a 1K-token context window.

- Model ID: baai/bge-large-en-v1.5
- Type: Embeddings
- Publisher: BAAI
- Context window: 512 tokens
- Input price: $0.01 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/baai/bge-large-en-v1.5

### BGE M3 (`baai/bge-m3`)

baai/bge-m3 is a text embedding model from BAAI you can call on the OceanToken API at $0.01 per 1M input tokens, with a 8K-token context window and up to 8K output tokens.

- Model ID: baai/bge-m3
- Type: Embeddings
- Publisher: BAAI
- Context window: 8,194 tokens
- Max output: 8,194 tokens
- Input price: $0.01 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/baai/bge-m3

## Black Forest Labs models

Index: https://docs.oceantoken.ai/models/black-forest-labs

### FLUX 3 Video (`black-forest-labs/flux-3-video`)

black-forest-labs/flux-3-video is a video generation model from Black Forest Labs you can call on the OceanToken API at from $0.17 per second of generated video.

- Model ID: black-forest-labs/flux-3-video
- Type: Video
- Publisher: Black Forest Labs
- Price: from $0.17 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-04
- Page: https://docs.oceantoken.ai/models/black-forest-labs/flux-3-video

### FLUX Video Edit (`black-forest-labs/flux-video-edit`)

black-forest-labs/flux-video-edit is a video generation model from Black Forest Labs you can call on the OceanToken API at from $0.03 per second of generated video.

- Model ID: black-forest-labs/flux-video-edit
- Type: Video
- Publisher: Black Forest Labs
- Price: from $0.03 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-10
- Page: https://docs.oceantoken.ai/models/black-forest-labs/flux-video-edit

### FLUX Video Upscale (`black-forest-labs/flux-video-upscale`)

black-forest-labs/flux-video-upscale is a video generation model from Black Forest Labs you can call on the OceanToken API at from $0.0143 per second of generated video.

- Model ID: black-forest-labs/flux-video-upscale
- Type: Video
- Publisher: Black Forest Labs
- Price: from $0.0143 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-19
- Page: https://docs.oceantoken.ai/models/black-forest-labs/flux-video-upscale

### Flux.2 Flex (`black-forest-labs/flux.2-flex`)

black-forest-labs/flux.2-flex is an image generation model from Black Forest Labs you can call on the OceanToken API at $0.06 per megapixel of output; it supports image input.

- Model ID: black-forest-labs/flux.2-flex
- Type: Image
- Publisher: Black Forest Labs
- Output price: $0.06 per megapixel
- Input price: $0.06 per megapixel of input images
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-25
- Page: https://docs.oceantoken.ai/models/black-forest-labs/flux.2-flex

### Flux.2 Klein 4B (`black-forest-labs/flux.2-klein-4b`)

black-forest-labs/flux.2-klein-4b is an image generation model from Black Forest Labs you can call on the OceanToken API at $0.014 per megapixel of output, then $0.001 per further megapixel; it supports image input.

- Model ID: black-forest-labs/flux.2-klein-4b
- Type: Image
- Publisher: Black Forest Labs
- Output price: $0.014 per megapixel for the first megapixel, then $0.001 per further megapixel
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-14
- Page: https://docs.oceantoken.ai/models/black-forest-labs/flux.2-klein-4b

### Flux.2 Max (`black-forest-labs/flux.2-max`)

black-forest-labs/flux.2-max is an image generation model from Black Forest Labs you can call on the OceanToken API at $0.07 per megapixel of output, then $0.03 per further megapixel; it supports image input.

- Model ID: black-forest-labs/flux.2-max
- Type: Image
- Publisher: Black Forest Labs
- Output price: $0.07 per megapixel for the first megapixel, then $0.03 per further megapixel
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-16
- Page: https://docs.oceantoken.ai/models/black-forest-labs/flux.2-max

### Flux.2 Pro (`black-forest-labs/flux.2-pro`)

black-forest-labs/flux.2-pro is an image generation model from Black Forest Labs you can call on the OceanToken API at $0.03 per megapixel of output, then $0.015 per further megapixel; it supports image input.

- Model ID: black-forest-labs/flux.2-pro
- Type: Image
- Publisher: Black Forest Labs
- Output price: $0.03 per megapixel for the first megapixel, then $0.015 per further megapixel
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-25
- Page: https://docs.oceantoken.ai/models/black-forest-labs/flux.2-pro

## ByteDance models

Index: https://docs.oceantoken.ai/models/bytedance

### Seedance 1.5 Pro (`bytedance/seedance-1-5-pro`)

bytedance/seedance-1-5-pro is a video generation model from ByteDance you can call on the OceanToken API at from $0.0115 per second of generated video.

- Model ID: bytedance/seedance-1-5-pro
- Type: Video
- Publisher: ByteDance
- Price: from $0.0115 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-23
- Page: https://docs.oceantoken.ai/models/bytedance/seedance-1-5-pro

### Seedance 2.0 (`bytedance/seedance-2.0`)

bytedance/seedance-2.0 is a video generation model from ByteDance you can call on the OceanToken API at from $0.0673 per second of generated video.

- Model ID: bytedance/seedance-2.0
- Type: Video
- Publisher: ByteDance
- Price: from $0.0673 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-15
- Page: https://docs.oceantoken.ai/models/bytedance/seedance-2.0

### Seedance 2.0 Fast (`bytedance/seedance-2.0-fast`)

bytedance/seedance-2.0-fast is a video generation model from ByteDance you can call on the OceanToken API at from $0.0404 per second of generated video.

- Model ID: bytedance/seedance-2.0-fast
- Type: Video
- Publisher: ByteDance
- Price: from $0.0404 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-15
- Page: https://docs.oceantoken.ai/models/bytedance/seedance-2.0-fast

### Seedance 2.0 Mini (`bytedance/seedance-2.0-mini`)

bytedance/seedance-2.0-mini is a video generation model from ByteDance you can call on the OceanToken API at from $0.0336 per second of generated video.

- Model ID: bytedance/seedance-2.0-mini
- Type: Video
- Publisher: ByteDance
- Price: from $0.0336 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-12
- Page: https://docs.oceantoken.ai/models/bytedance/seedance-2.0-mini

### Seedance 2.5 (`bytedance/seedance-2.5`)

bytedance/seedance-2.5 is a video generation model from ByteDance you can call on the OceanToken API at from $0.103 per second of generated video.

- Model ID: bytedance/seedance-2.5
- Type: Video
- Publisher: ByteDance
- Price: from $0.103 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-07
- Page: https://docs.oceantoken.ai/models/bytedance/seedance-2.5

### Ui Tars 1.5 7B (`bytedance/ui-tars-1.5-7b`)

bytedance/ui-tars-1.5-7b is a language model from ByteDance you can call on the OceanToken API at $0.10 per 1M input tokens and $0.20 per 1M output tokens, with a 128K-token context window and up to 2K output tokens; it supports image input.

- Model ID: bytedance/ui-tars-1.5-7b
- Type: Text
- Publisher: ByteDance
- Context window: 128,000 tokens
- Max output: 2,048 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.20 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Capabilities: image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-22
- Page: https://docs.oceantoken.ai/models/bytedance/ui-tars-1.5-7b

## ByteDance Seed models

Index: https://docs.oceantoken.ai/models/bytedance-seed

### Seed-1.6 (`bytedance-seed/seed-1.6`)

bytedance-seed/seed-1.6 is a language model from ByteDance Seed you can call on the OceanToken API at $0.25 per 1M input tokens and $2.00 per 1M output tokens, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: bytedance-seed/seed-1.6
- Type: Text
- Publisher: ByteDance Seed
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Input price: $0.25 per 1M tokens
- Output price: $2.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-23
- Scheduled retirement: 2026-11-11
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seed-1.6

### Seed-1.6 Flash (`bytedance-seed/seed-1.6-flash`)

bytedance-seed/seed-1.6-flash is a language model from ByteDance Seed you can call on the OceanToken API at $0.075 per 1M input tokens and $0.30 per 1M output tokens, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: bytedance-seed/seed-1.6-flash
- Type: Text
- Publisher: ByteDance Seed
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Input price: $0.075 per 1M tokens
- Output price: $0.30 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-23
- Scheduled retirement: 2026-11-11
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seed-1.6-flash

### Seed-2 1 Turbo (`bytedance-seed/seed-2-1-turbo`)

bytedance-seed/seed-2-1-turbo is a language model from ByteDance Seed you can call on the OceanToken API at $0.50 per 1M input tokens and $2.50 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: bytedance-seed/seed-2-1-turbo
- Type: Text
- Publisher: ByteDance Seed
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.50 per 1M tokens
- Output price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-12
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seed-2-1-turbo

### Seed-2.0 Code (`bytedance-seed/seed-2.0-code`)

bytedance-seed/seed-2.0-code is a language model from ByteDance Seed you can call on the OceanToken API at $0.50 per 1M input tokens and $3.00 per 1M output tokens, with a 262K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: bytedance-seed/seed-2.0-code
- Type: Text
- Publisher: ByteDance Seed
- Context window: 262,144 tokens
- Max output: 131,072 tokens
- Input price: $0.50 per 1M tokens
- Output price: $3.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-12
- Scheduled retirement: 2026-11-11
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seed-2.0-code

### Seed-2.0 Lite (`bytedance-seed/seed-2.0-lite`)

bytedance-seed/seed-2.0-lite is a language model from ByteDance Seed you can call on the OceanToken API at $0.25 per 1M input tokens and $2.00 per 1M output tokens, with a 262K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: bytedance-seed/seed-2.0-lite
- Type: Text
- Publisher: ByteDance Seed
- Context window: 262,144 tokens
- Max output: 131,072 tokens
- Input price: $0.25 per 1M tokens
- Output price: $2.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-10
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seed-2.0-lite

### Seed-2.0 Mini (`bytedance-seed/seed-2.0-mini`)

bytedance-seed/seed-2.0-mini is a language model from ByteDance Seed you can call on the OceanToken API at $0.10 per 1M input tokens and $0.40 per 1M output tokens, with a 262K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: bytedance-seed/seed-2.0-mini
- Type: Text
- Publisher: ByteDance Seed
- Context window: 262,144 tokens
- Max output: 131,072 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.40 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-26
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seed-2.0-mini

### Seedream 4.5 (`bytedance-seed/seedream-4.5`)

bytedance-seed/seedream-4.5 is an image generation model from ByteDance Seed you can call on the OceanToken API at $0.04 per generated image; it supports image input.

- Model ID: bytedance-seed/seedream-4.5
- Type: Image
- Publisher: ByteDance Seed
- Price: $0.04 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-23
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seedream-4.5

### Seedream 5.0 Lite (`bytedance-seed/seedream-5-0-lite`)

bytedance-seed/seedream-5-0-lite is an image generation model from ByteDance Seed you can call on the OceanToken API at $0.035 per generated image; it supports image input.

- Model ID: bytedance-seed/seedream-5-0-lite
- Type: Image
- Publisher: ByteDance Seed
- Price: $0.035 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seedream-5-0-lite

### Seedream 5.0 Pro (`bytedance-seed/seedream-5-0-pro`)

bytedance-seed/seedream-5-0-pro is an image generation model from ByteDance Seed you can call on the OceanToken API at $0.09 per generated image; it supports image input.

- Model ID: bytedance-seed/seedream-5-0-pro
- Type: Image
- Publisher: ByteDance Seed
- Price: $0.09 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-12
- Page: https://docs.oceantoken.ai/models/bytedance-seed/seedream-5-0-pro

## Canopylabs models

Index: https://docs.oceantoken.ai/models/canopylabs

### Orpheus 3B 0.1 Ft (`canopylabs/orpheus-3b-0.1-ft`)

canopylabs/orpheus-3b-0.1-ft is a text-to-speech model from Canopylabs you can call on the OceanToken API at $0.007 per 1,000 characters.

- Model ID: canopylabs/orpheus-3b-0.1-ft
- Type: Speech
- Publisher: Canopylabs
- Price: $0.007 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-23
- Page: https://docs.oceantoken.ai/models/canopylabs/orpheus-3b-0.1-ft

## Cognitivecomputations models

Index: https://docs.oceantoken.ai/models/cognitivecomputations

### Dolphin Mistral 24B Venice Edition (`cognitivecomputations/dolphin-mistral-24b-venice-edition`)

cognitivecomputations/dolphin-mistral-24b-venice-edition is a language model from Cognitivecomputations you can call on the OceanToken API at $0.20 per 1M input tokens and $0.90 per 1M output tokens, with a 128K-token context window and up to 8K output tokens.

- Model ID: cognitivecomputations/dolphin-mistral-24b-venice-edition
- Type: Text
- Publisher: Cognitivecomputations
- Context window: 128,000 tokens
- Max output: 8,192 tokens
- Input price: $0.20 per 1M tokens
- Output price: $0.90 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-09
- Page: https://docs.oceantoken.ai/models/cognitivecomputations/dolphin-mistral-24b-venice-edition

## Cohere models

Index: https://docs.oceantoken.ai/models/cohere

### Command A (`cohere/command-a`)

cohere/command-a is a language model from Cohere you can call on the OceanToken API at $2.50 per 1M input tokens and $10.00 per 1M output tokens, with a 256K-token context window and up to 8K output tokens.

- Model ID: cohere/command-a
- Type: Text
- Publisher: Cohere
- Context window: 256,000 tokens
- Max output: 8,192 tokens
- Input price: $2.50 per 1M tokens
- Output price: $10.00 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-13
- Page: https://docs.oceantoken.ai/models/cohere/command-a

### Command R 08.2024 (`cohere/command-r-08-2024`)

cohere/command-r-08-2024 is a language model from Cohere you can call on the OceanToken API at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 128K-token context window and up to 4K output tokens; it supports tool calling.

- Model ID: cohere/command-r-08-2024
- Type: Text
- Publisher: Cohere
- Context window: 128,000 tokens
- Max output: 4,000 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.60 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-08-30
- Page: https://docs.oceantoken.ai/models/cohere/command-r-08-2024

### Command R Plus 08.2024 (`cohere/command-r-plus-08-2024`)

cohere/command-r-plus-08-2024 is a language model from Cohere you can call on the OceanToken API at $2.50 per 1M input tokens and $10.00 per 1M output tokens, with a 128K-token context window and up to 4K output tokens; it supports tool calling.

- Model ID: cohere/command-r-plus-08-2024
- Type: Text
- Publisher: Cohere
- Context window: 128,000 tokens
- Max output: 4,000 tokens
- Input price: $2.50 per 1M tokens
- Output price: $10.00 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-08-30
- Page: https://docs.oceantoken.ai/models/cohere/command-r-plus-08-2024

### Command R7b 12.2024 (`cohere/command-r7b-12-2024`)

cohere/command-r7b-12-2024 is a language model from Cohere you can call on the OceanToken API at $0.0375 per 1M input tokens and $0.15 per 1M output tokens, with a 128K-token context window and up to 4K output tokens.

- Model ID: cohere/command-r7b-12-2024
- Type: Text
- Publisher: Cohere
- Context window: 128,000 tokens
- Max output: 4,000 tokens
- Input price: $0.0375 per 1M tokens
- Output price: $0.15 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-14
- Page: https://docs.oceantoken.ai/models/cohere/command-r7b-12-2024

### North Mini Code (Free) (`cohere/north-mini-code:free`)

cohere/north-mini-code:free is a language model from Cohere you can call free of charge on the OceanToken API, rate-limited, with a 256K-token context window and up to 64K output tokens; it supports reasoning, tool calling.

- Model ID: cohere/north-mini-code:free
- Type: Text
- Publisher: Cohere
- Context window: 256,000 tokens
- Max output: 64,000 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-17
- Page: https://docs.oceantoken.ai/models/cohere/north-mini-code--free

### Rerank 4 Fast (`cohere/rerank-4-fast`)

cohere/rerank-4-fast is a reranking model from Cohere you can call on the OceanToken API at $0.002 per search unit.

- Model ID: cohere/rerank-4-fast
- Type: Rerank
- Publisher: Cohere
- Price: $0.002 per search unit
- Endpoint: /v1/rerank
- API shape: Cohere rerank
- In the catalog since: 2026-04-06
- Page: https://docs.oceantoken.ai/models/cohere/rerank-4-fast

### Rerank 4 Pro (`cohere/rerank-4-pro`)

cohere/rerank-4-pro is a reranking model from Cohere you can call on the OceanToken API at $0.0025 per search unit.

- Model ID: cohere/rerank-4-pro
- Type: Rerank
- Publisher: Cohere
- Price: $0.0025 per search unit
- Endpoint: /v1/rerank
- API shape: Cohere rerank
- In the catalog since: 2026-04-06
- Page: https://docs.oceantoken.ai/models/cohere/rerank-4-pro

### Rerank V3.5 (`cohere/rerank-v3.5`)

cohere/rerank-v3.5 is a reranking model from Cohere you can call on the OceanToken API at $0.001 per search unit.

- Model ID: cohere/rerank-v3.5
- Type: Rerank
- Publisher: Cohere
- Price: $0.001 per search unit
- Endpoint: /v1/rerank
- API shape: Cohere rerank
- In the catalog since: 2026-04-05
- Page: https://docs.oceantoken.ai/models/cohere/rerank-v3.5

## Deepgram models

Index: https://docs.oceantoken.ai/models/deepgram

### Aura 2 (`deepgram/aura-2`)

deepgram/aura-2 is a text-to-speech model from Deepgram you can call on the OceanToken API at $0.03 per 1,000 characters.

- Model ID: deepgram/aura-2
- Type: Speech
- Publisher: Deepgram
- Price: $0.03 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-16
- Page: https://docs.oceantoken.ai/models/deepgram/aura-2

### Nova 3 (`deepgram/nova-3`)

deepgram/nova-3 is a speech-to-text model from Deepgram you can call on the OceanToken API at $0.0043 per minute of audio.

- Model ID: deepgram/nova-3
- Type: Transcription
- Publisher: Deepgram
- Price: $0.0043 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-15
- Page: https://docs.oceantoken.ai/models/deepgram/nova-3

## DeepSeek models

Index: https://docs.oceantoken.ai/models/deepseek

### DeepSeek Chat (`deepseek/deepseek-chat`)

deepseek/deepseek-chat is a language model from DeepSeek you can call on the OceanToken API at $0.256 per 1M input tokens and $0.712 per 1M output tokens, with a 164K-token context window and up to 16K output tokens; it supports tool calling.

- Model ID: deepseek/deepseek-chat
- Type: Text
- Publisher: DeepSeek
- Context window: 163,840 tokens
- Max output: 16,384 tokens
- Input price: $0.256 per 1M tokens
- Output price: $0.712 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-26
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-chat

### DeepSeek Chat V3 0324 (`deepseek/deepseek-chat-v3-0324`)

deepseek/deepseek-chat-v3-0324 is a language model from DeepSeek you can call on the OceanToken API at $0.25 per 1M input tokens and $1.00 per 1M output tokens, with a 164K-token context window and up to 115K output tokens; it supports tool calling.

- Model ID: deepseek/deepseek-chat-v3-0324
- Type: Text
- Publisher: DeepSeek
- Context window: 163,840 tokens
- Max output: 115,200 tokens
- Input price: $0.25 per 1M tokens
- Output price: $1.00 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-24
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-chat-v3-0324

### DeepSeek Chat V3.1 (`deepseek/deepseek-chat-v3.1`)

deepseek/deepseek-chat-v3.1 is a language model from DeepSeek you can call on the OceanToken API at $0.55 per 1M input tokens and $1.65 per 1M output tokens, with a 164K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-chat-v3.1
- Type: Text
- Publisher: DeepSeek
- Context window: 163,840 tokens
- Max output: 32,768 tokens
- Input price: $0.55 per 1M tokens
- Output price: $1.65 per 1M tokens
- Cached input price: $0.55 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-21
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-chat-v3.1

### DeepSeek Flash Latest (`deepseek/deepseek-flash-latest`)

deepseek/deepseek-flash-latest is a language model from DeepSeek you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: deepseek/deepseek-flash-latest
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.006 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: deepseek/deepseek-v4.1-flash-1017
- In the catalog since: 2026-09-14
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-flash-latest

### DeepSeek Pro Latest (`deepseek/deepseek-pro-latest`)

deepseek/deepseek-pro-latest is a language model from DeepSeek you can call on the OceanToken API at $1.32 per 1M input tokens and $3.96 per 1M output tokens, with a 1.05M-token context window and up to 393K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-pro-latest
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 393,216 tokens
- Input price: $1.32 per 1M tokens
- Output price: $3.96 per 1M tokens
- Cached input price: $0.044 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: deepseek/deepseek-v4-pro-0813
- In the catalog since: 2026-09-14
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-pro-latest

### DeepSeek R1 (`deepseek/deepseek-r1`)

deepseek/deepseek-r1 is a language model from DeepSeek you can call on the OceanToken API at $0.70 per 1M input tokens and $2.50 per 1M output tokens, with a 64K-token context window and up to 16K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-r1
- Type: Text
- Publisher: DeepSeek
- Context window: 64,000 tokens
- Max output: 16,000 tokens
- Input price: $0.70 per 1M tokens
- Output price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-01-20
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-r1

### DeepSeek R1 0528 (`deepseek/deepseek-r1-0528`)

deepseek/deepseek-r1-0528 is a language model from DeepSeek you can call on the OceanToken API at $0.571 per 1M input tokens and $2.286 per 1M output tokens, with a 164K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-r1-0528
- Type: Text
- Publisher: DeepSeek
- Context window: 163,840 tokens
- Max output: 32,768 tokens
- Input price: $0.571 per 1M tokens
- Output price: $2.286 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-05-28
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-r1-0528

### DeepSeek V3.1 Terminus (`deepseek/deepseek-v3.1-terminus`)

deepseek/deepseek-v3.1-terminus is a language model from DeepSeek you can call on the OceanToken API at $0.27 per 1M input tokens and $1.00 per 1M output tokens, with a 164K-token context window and up to 147K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v3.1-terminus
- Type: Text
- Publisher: DeepSeek
- Context window: 163,840 tokens
- Max output: 147,456 tokens
- Input price: $0.27 per 1M tokens
- Output price: $1.00 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-22
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v3.1-terminus

### DeepSeek V3.2 (`deepseek/deepseek-v3.2`)

deepseek/deepseek-v3.2 is a language model from DeepSeek you can call on the OceanToken API at $0.30 per 1M input tokens and $0.96 per 1M output tokens, with a 164K-token context window and up to 66K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v3.2
- Type: Text
- Publisher: DeepSeek
- Context window: 163,840 tokens
- Max output: 65,536 tokens
- Input price: $0.30 per 1M tokens
- Output price: $0.96 per 1M tokens
- Cached input price: $0.09 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-01
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v3.2

### DeepSeek V3.2 Exp (`deepseek/deepseek-v3.2-exp`)

deepseek/deepseek-v3.2-exp is a language model from DeepSeek you can call on the OceanToken API at $0.27 per 1M input tokens and $0.41 per 1M output tokens, with a 164K-token context window and up to 147K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v3.2-exp
- Type: Text
- Publisher: DeepSeek
- Context window: 163,840 tokens
- Max output: 147,456 tokens
- Input price: $0.27 per 1M tokens
- Output price: $0.41 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-29
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v3.2-exp

### DeepSeek V4 Flash (`deepseek/deepseek-v4-flash`)

deepseek/deepseek-v4-flash is a language model from DeepSeek you can call on the OceanToken API at $0.098 per 1M input tokens and $0.196 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v4-flash
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 943,717 tokens
- Input price: $0.098 per 1M tokens
- Output price: $0.196 per 1M tokens
- Cached input price: $0.0196 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-24
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v4-flash

### DeepSeek V4 Flash 0731 (`deepseek/deepseek-v4-flash-0731`)

deepseek/deepseek-v4-flash-0731 is a language model from DeepSeek you can call on the OceanToken API at $0.13 per 1M input tokens and $0.28 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v4-flash-0731
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $0.13 per 1M tokens
- Output price: $0.28 per 1M tokens
- Cached input price: $0.07 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-31
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v4-flash-0731

### DeepSeek V4 Flash Latest (`deepseek/deepseek-v4-flash-latest`)

deepseek/deepseek-v4-flash-latest is a language model from DeepSeek you can call on the OceanToken API at $0.13 per 1M input tokens and $0.28 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v4-flash-latest
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $0.13 per 1M tokens
- Output price: $0.28 per 1M tokens
- Cached input price: $0.07 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: deepseek/deepseek-v4-flash-0731
- In the catalog since: 2026-08-01
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v4-flash-latest

### DeepSeek V4 Flash Vision Exp (`deepseek/deepseek-v4-flash-vision-exp`)

deepseek/deepseek-v4-flash-vision-exp is a language model from DeepSeek you can call on the OceanToken API at $0.44 per 1M input tokens and $1.32 per 1M output tokens, with a 1.05M-token context window and up to 262K output tokens; it supports reasoning, tool calling, image input.

- Model ID: deepseek/deepseek-v4-flash-vision-exp
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 262,144 tokens
- Input price: $0.44 per 1M tokens
- Output price: $1.32 per 1M tokens
- Cached input price: $0.014 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-21
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v4-flash-vision-exp

### DeepSeek V4 Pro (`deepseek/deepseek-v4-pro`)

deepseek/deepseek-v4-pro is a language model from DeepSeek you can call on the OceanToken API at $1.15 per 1M input tokens and $2.55 per 1M output tokens, with a 1.05M-token context window and up to 384K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v4-pro
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 384,000 tokens
- Input price: $1.15 per 1M tokens
- Output price: $2.55 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-24
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v4-pro

### DeepSeek V4 Pro 0813 (`deepseek/deepseek-v4-pro-0813`)

deepseek/deepseek-v4-pro-0813 is a language model from DeepSeek you can call on the OceanToken API at $1.32 per 1M input tokens and $3.96 per 1M output tokens, with a 1.05M-token context window and up to 393K output tokens; it supports reasoning, tool calling.

- Model ID: deepseek/deepseek-v4-pro-0813
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 393,216 tokens
- Input price: $1.32 per 1M tokens
- Output price: $3.96 per 1M tokens
- Cached input price: $0.044 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-12
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v4-pro-0813

### DeepSeek V4.1 Flash (`deepseek/deepseek-v4.1-flash`)

deepseek/deepseek-v4.1-flash is a language model from DeepSeek you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 1.05M-token context window and up to 393K output tokens; it supports reasoning, tool calling, image input.

- Model ID: deepseek/deepseek-v4.1-flash
- Type: Text
- Publisher: DeepSeek
- Context window: 1,048,576 tokens
- Max output: 393,216 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.006 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-10
- Page: https://docs.oceantoken.ai/models/deepseek/deepseek-v4.1-flash

## Dots Studio models

Index: https://docs.oceantoken.ai/models/dots-studio

### dots 3 Note Preview (Free) (`dots-studio/dots-3-note-preview:free`)

dots-studio/dots-3-note-preview:free is a language model from Dots Studio you can call free of charge on the OceanToken API, rate-limited, with a 512K-token context window and up to 461K output tokens; it supports reasoning, tool calling, image input.

- Model ID: dots-studio/dots-3-note-preview:free
- Type: Text
- Publisher: Dots Studio
- Context window: 512,000 tokens
- Max output: 460,800 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-14
- Scheduled retirement: 2026-12-31
- Page: https://docs.oceantoken.ai/models/dots-studio/dots-3-note-preview--free

## Fish Audio models

Index: https://docs.oceantoken.ai/models/fish-audio

### S1 (`fish-audio/s1`)

fish-audio/s1 is a text-to-speech model from Fish Audio you can call on the OceanToken API at $0.015 per 1,000 characters.

- Model ID: fish-audio/s1
- Type: Speech
- Publisher: Fish Audio
- Price: $0.015 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/fish-audio/s1

### S2 Pro (`fish-audio/s2-pro`)

fish-audio/s2-pro is a text-to-speech model from Fish Audio you can call on the OceanToken API at $0.015 per 1,000 characters.

- Model ID: fish-audio/s2-pro
- Type: Speech
- Publisher: Fish Audio
- Price: $0.015 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/fish-audio/s2-pro

### S2.1 Pro (`fish-audio/s2.1-pro`)

fish-audio/s2.1-pro is a text-to-speech model from Fish Audio you can call on the OceanToken API at $0.015 per 1,000 characters.

- Model ID: fish-audio/s2.1-pro
- Type: Speech
- Publisher: Fish Audio
- Price: $0.015 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/fish-audio/s2.1-pro

### S2.1 Pro Free (Free) (`fish-audio/s2.1-pro-free:free`)

fish-audio/s2.1-pro-free:free is a text-to-speech model from Fish Audio you can call free of charge on the OceanToken API, rate-limited.

- Model ID: fish-audio/s2.1-pro-free:free
- Type: Speech
- Publisher: Fish Audio
- Price: Free, rate-limited
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/fish-audio/s2.1-pro-free--free

### Transcribe 1 (`fish-audio/transcribe-1`)

fish-audio/transcribe-1 is a speech-to-text model from Fish Audio you can call on the OceanToken API at $0.006 per minute of audio.

- Model ID: fish-audio/transcribe-1
- Type: Transcription
- Publisher: Fish Audio
- Price: $0.006 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/fish-audio/transcribe-1

## Google models

Index: https://docs.oceantoken.ai/models/google

### Chirp 3 (`google/chirp-3`)

google/chirp-3 is a speech-to-text model from Google you can call on the OceanToken API at $0.016 per minute of audio.

- Model ID: google/chirp-3
- Type: Transcription
- Publisher: Google
- Price: $0.016 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-05
- Page: https://docs.oceantoken.ai/models/google/chirp-3

### Gemini 2.5 Flash (`google/gemini-2.5-flash`)

google/gemini-2.5-flash is a language model from Google you can call on the OceanToken API at $0.30 per 1M input tokens and $2.50 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input, audio output.

- Model ID: google/gemini-2.5-flash
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,535 tokens
- Input price: $0.30 per 1M tokens
- Output price: $2.50 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Cache write price: $0.383 per 1M tokens
- Capabilities: reasoning, tool calling, image input, audio output
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-06-17
- Scheduled retirement: 2026-10-20
- Page: https://docs.oceantoken.ai/models/google/gemini-2.5-flash

### Gemini 2.5 Flash Image (`google/gemini-2.5-flash-image`)

google/gemini-2.5-flash-image is an image generation model from Google you can call on the OceanToken API at $0.30 per 1M input tokens and $30.00 per 1M output tokens, with a 33K-token context window and up to 8K output tokens; it supports image input.

- Model ID: google/gemini-2.5-flash-image
- Type: Image
- Publisher: Google
- Context window: 32,768 tokens
- Max output: 8,192 tokens
- Input price: $0.30 per 1M tokens
- Output price: $30.00 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Cache write price: $0.383 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-07
- Page: https://docs.oceantoken.ai/models/google/gemini-2.5-flash-image

### Gemini 2.5 Flash Lite (`google/gemini-2.5-flash-lite`)

google/gemini-2.5-flash-lite is a language model from Google you can call on the OceanToken API at $0.10 per 1M input tokens and $0.40 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-2.5-flash-lite
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,535 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.40 per 1M tokens
- Cached input price: $0.01 per 1M tokens
- Cache write price: $0.183 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-22
- Scheduled retirement: 2026-10-20
- Page: https://docs.oceantoken.ai/models/google/gemini-2.5-flash-lite

### Gemini 2.5 Pro (`google/gemini-2.5-pro`)

google/gemini-2.5-pro is a language model from Google you can call on the OceanToken API at $1.25 per 1M input tokens and $10.00 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input, audio output.

- Model ID: google/gemini-2.5-pro
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $1.25 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.125 per 1M tokens
- Cache write price: $1.625 per 1M tokens
- Capabilities: reasoning, tool calling, image input, audio output
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-06-17
- Scheduled retirement: 2026-10-20
- Page: https://docs.oceantoken.ai/models/google/gemini-2.5-pro

### Gemini 2.5 Pro Preview (`google/gemini-2.5-pro-preview`)

google/gemini-2.5-pro-preview is a language model from Google you can call on the OceanToken API at $1.25 per 1M input tokens and $10.00 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-2.5-pro-preview
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $1.25 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.125 per 1M tokens
- Cache write price: $1.625 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-06-05
- Page: https://docs.oceantoken.ai/models/google/gemini-2.5-pro-preview

### Gemini 3 Flash Preview (`google/gemini-3-flash-preview`)

google/gemini-3-flash-preview is a language model from Google you can call on the OceanToken API at $0.50 per 1M input tokens and $3.00 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: google/gemini-3-flash-preview
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.50 per 1M tokens
- Output price: $3.00 per 1M tokens
- Cached input price: $0.05 per 1M tokens
- Cache write price: $0.583 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-17
- Page: https://docs.oceantoken.ai/models/google/gemini-3-flash-preview

### Gemini 3 Pro Image (`google/gemini-3-pro-image`)

google/gemini-3-pro-image is an image generation model from Google you can call on the OceanToken API at $2.00 per 1M input tokens and $12.00 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3-pro-image
- Type: Image
- Publisher: Google
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $2.00 per 1M tokens
- Output price: $12.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-18
- Page: https://docs.oceantoken.ai/models/google/gemini-3-pro-image

### Gemini 3 Pro Image Preview (`google/gemini-3-pro-image-preview`)

google/gemini-3-pro-image-preview is an image generation model from Google you can call on the OceanToken API at $2.00 per 1M input tokens and $60.00 per 1M output tokens, with a 66K-token context window and up to 33K output tokens; it supports reasoning, image input.

- Model ID: google/gemini-3-pro-image-preview
- Type: Image
- Publisher: Google
- Context window: 65,536 tokens
- Max output: 32,768 tokens
- Input price: $2.00 per 1M tokens
- Output price: $60.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.375 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-20
- Page: https://docs.oceantoken.ai/models/google/gemini-3-pro-image-preview

### Gemini 3.1 Flash Image (`google/gemini-3.1-flash-image`)

google/gemini-3.1-flash-image is an image generation model from Google you can call on the OceanToken API at $0.50 per 1M input tokens and $3.00 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, image input.

- Model ID: google/gemini-3.1-flash-image
- Type: Image
- Publisher: Google
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $0.50 per 1M tokens
- Output price: $3.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-18
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-flash-image

### Gemini 3.1 Flash Image Preview (`google/gemini-3.1-flash-image-preview`)

google/gemini-3.1-flash-image-preview is an image generation model from Google you can call on the OceanToken API at $0.50 per 1M input tokens and $60.00 per 1M output tokens, with a 66K-token context window and up to 59K output tokens; it supports reasoning, image input.

- Model ID: google/gemini-3.1-flash-image-preview
- Type: Image
- Publisher: Google
- Context window: 65,536 tokens
- Max output: 58,982 tokens
- Input price: $0.50 per 1M tokens
- Output price: $60.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-26
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-flash-image-preview

### Gemini 3.1 Flash Lite (`google/gemini-3.1-flash-lite`)

google/gemini-3.1-flash-lite is a language model from Google you can call on the OceanToken API at $0.25 per 1M input tokens and $1.50 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.1-flash-lite
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.25 per 1M tokens
- Output price: $1.50 per 1M tokens
- Cached input price: $0.025 per 1M tokens
- Cache write price: $0.333 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-07
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-flash-lite

### Gemini 3.1 Flash Lite Image (`google/gemini-3.1-flash-lite-image`)

google/gemini-3.1-flash-lite-image is an image generation model from Google you can call on the OceanToken API at $0.25 per 1M input tokens and $30.00 per 1M output tokens, with a 66K-token context window and up to 59K output tokens; it supports reasoning, image input.

- Model ID: google/gemini-3.1-flash-lite-image
- Type: Image
- Publisher: Google
- Context window: 65,536 tokens
- Max output: 58,982 tokens
- Input price: $0.25 per 1M tokens
- Output price: $30.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-30
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-flash-lite-image

### Gemini 3.1 Flash Lite Preview (`google/gemini-3.1-flash-lite-preview`)

google/gemini-3.1-flash-lite-preview is a language model from Google you can call on the OceanToken API at $0.25 per 1M input tokens and $1.50 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: google/gemini-3.1-flash-lite-preview
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.25 per 1M tokens
- Output price: $1.50 per 1M tokens
- Cached input price: $0.025 per 1M tokens
- Cache write price: $0.333 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-03
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-flash-lite-preview

### Gemini 3.1 Flash TTS Preview (`google/gemini-3.1-flash-tts-preview`)

google/gemini-3.1-flash-tts-preview is a text-to-speech model from Google you can call on the OceanToken API at $0.001 per 1,000 characters.

- Model ID: google/gemini-3.1-flash-tts-preview
- Type: Speech
- Publisher: Google
- Price: $0.001 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-24
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-flash-tts-preview

### Gemini 3.1 Pro Preview (`google/gemini-3.1-pro-preview`)

google/gemini-3.1-pro-preview is a language model from Google you can call on the OceanToken API at $2.00 per 1M input tokens and $12.00 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.1-pro-preview
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $2.00 per 1M tokens
- Output price: $12.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.375 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-19
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-pro-preview

### Gemini 3.1 Pro Preview Customtools (`google/gemini-3.1-pro-preview-customtools`)

google/gemini-3.1-pro-preview-customtools is a language model from Google you can call on the OceanToken API at $2.00 per 1M input tokens and $12.00 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.1-pro-preview-customtools
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $2.00 per 1M tokens
- Output price: $12.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.375 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-25
- Page: https://docs.oceantoken.ai/models/google/gemini-3.1-pro-preview-customtools

### Gemini 3.5 Flash (`google/gemini-3.5-flash`)

google/gemini-3.5-flash is a language model from Google you can call on the OceanToken API at $1.50 per 1M input tokens and $9.00 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.5-flash
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $1.50 per 1M tokens
- Output price: $9.00 per 1M tokens
- Cached input price: $0.15 per 1M tokens
- Cache write price: $1.583 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-19
- Page: https://docs.oceantoken.ai/models/google/gemini-3.5-flash

### Gemini 3.5 Flash Lite (`google/gemini-3.5-flash-lite`)

google/gemini-3.5-flash-lite is a language model from Google you can call on the OceanToken API at $0.30 per 1M input tokens and $2.50 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.5-flash-lite
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.30 per 1M tokens
- Output price: $2.50 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Cache write price: $0.383 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-21
- Page: https://docs.oceantoken.ai/models/google/gemini-3.5-flash-lite

### Gemini 3.6 Flash (`google/gemini-3.6-flash`)

google/gemini-3.6-flash is a language model from Google you can call on the OceanToken API at $0.75 per 1M input tokens and $3.75 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.6-flash
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.75 per 1M tokens
- Output price: $3.75 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Cache write price: $0.792 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-21
- Page: https://docs.oceantoken.ai/models/google/gemini-3.6-flash

### Gemini 3.7 Flash (`google/gemini-3.7-flash`)

google/gemini-3.7-flash is a language model from Google you can call on the OceanToken API at $0.75 per 1M input tokens and $3.75 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.7-flash
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.75 per 1M tokens
- Output price: $3.75 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Cache write price: $0.792 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/google/gemini-3.7-flash

### Gemini 3.8 Flash (`google/gemini-3.8-flash`)

google/gemini-3.8-flash is a language model from Google you can call on the OceanToken API at $0.75 per 1M input tokens and $3.75 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-3.8-flash
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.75 per 1M tokens
- Output price: $3.75 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Cache write price: $0.792 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-02
- Page: https://docs.oceantoken.ai/models/google/gemini-3.8-flash

### Gemini Embedding 001 (`google/gemini-embedding-001`)

google/gemini-embedding-001 is a text embedding model from Google you can call on the OceanToken API at $0.15 per 1M input tokens, with a 20K-token context window.

- Model ID: google/gemini-embedding-001
- Type: Embeddings
- Publisher: Google
- Context window: 20,000 tokens
- Input price: $0.15 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-31
- Page: https://docs.oceantoken.ai/models/google/gemini-embedding-001

### Gemini Embedding 2 (`google/gemini-embedding-2`)

google/gemini-embedding-2 is a text embedding model from Google you can call on the OceanToken API at $0.20 per 1M input tokens, with a 8K-token context window.

- Model ID: google/gemini-embedding-2
- Type: Embeddings
- Publisher: Google
- Context window: 8,192 tokens
- Input price: $0.20 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-20
- Page: https://docs.oceantoken.ai/models/google/gemini-embedding-2

### Gemini Embedding 2 Preview (`google/gemini-embedding-2-preview`)

google/gemini-embedding-2-preview is a text embedding model from Google you can call on the OceanToken API at $0.20 per 1M input tokens, with a 8K-token context window.

- Model ID: google/gemini-embedding-2-preview
- Type: Embeddings
- Publisher: Google
- Context window: 8,192 tokens
- Input price: $0.20 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-17
- Page: https://docs.oceantoken.ai/models/google/gemini-embedding-2-preview

### Gemini Flash Latest (`google/gemini-flash-latest`)

google/gemini-flash-latest is a language model from Google you can call on the OceanToken API at $0.75 per 1M input tokens and $3.75 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-flash-latest
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $0.75 per 1M tokens
- Output price: $3.75 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Cache write price: $0.792 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: google/gemini-3.8-flash
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/google/gemini-flash-latest

### Gemini Pro Latest (`google/gemini-pro-latest`)

google/gemini-pro-latest is a language model from Google you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1.05M-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemini-pro-latest
- Type: Text
- Publisher: Google
- Context window: 1,048,576 tokens
- Max output: 65,536 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Cache write price: $2.188 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: google/gemini-4-argon
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/google/gemini-pro-latest

### Gemma 2 27B IT (`google/gemma-2-27b-it`)

google/gemma-2-27b-it is a language model from Google you can call on the OceanToken API at $0.65 per 1M input tokens and $0.65 per 1M output tokens, with a 8K-token context window and up to 2K output tokens.

- Model ID: google/gemma-2-27b-it
- Type: Text
- Publisher: Google
- Context window: 8,192 tokens
- Max output: 2,048 tokens
- Input price: $0.65 per 1M tokens
- Output price: $0.65 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-07-13
- Page: https://docs.oceantoken.ai/models/google/gemma-2-27b-it

### Gemma 3 12B IT (`google/gemma-3-12b-it`)

google/gemma-3-12b-it is a language model from Google you can call on the OceanToken API at $0.05 per 1M input tokens and $0.15 per 1M output tokens, with a 131K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: google/gemma-3-12b-it
- Type: Text
- Publisher: Google
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.05 per 1M tokens
- Output price: $0.15 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-13
- Page: https://docs.oceantoken.ai/models/google/gemma-3-12b-it

### Gemma 3 27B IT (`google/gemma-3-27b-it`)

google/gemma-3-27b-it is a language model from Google you can call on the OceanToken API at $0.08 per 1M input tokens and $0.45 per 1M output tokens, with a 131K-token context window and up to 118K output tokens; it supports tool calling, image input.

- Model ID: google/gemma-3-27b-it
- Type: Text
- Publisher: Google
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.08 per 1M tokens
- Output price: $0.45 per 1M tokens
- Cached input price: $0.04 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-12
- Page: https://docs.oceantoken.ai/models/google/gemma-3-27b-it

### Gemma 3 4B IT (`google/gemma-3-4b-it`)

google/gemma-3-4b-it is a language model from Google you can call on the OceanToken API at $0.04 per 1M input tokens and $0.05 per 1M output tokens, with a 131K-token context window and up to 16K output tokens; it supports image input.

- Model ID: google/gemma-3-4b-it
- Type: Text
- Publisher: Google
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.04 per 1M tokens
- Output price: $0.05 per 1M tokens
- Cached input price: $0.02 per 1M tokens
- Capabilities: image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-13
- Page: https://docs.oceantoken.ai/models/google/gemma-3-4b-it

### Gemma 4 26B A4B IT (`google/gemma-4-26b-a4b-it`)

google/gemma-4-26b-a4b-it is a language model from Google you can call on the OceanToken API at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemma-4-26b-a4b-it
- Type: Text
- Publisher: Google
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.60 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-03
- Page: https://docs.oceantoken.ai/models/google/gemma-4-26b-a4b-it

### Gemma 4 26B A4B IT (Free) (`google/gemma-4-26b-a4b-it:free`)

google/gemma-4-26b-a4b-it:free is a language model from Google you can call free of charge on the OceanToken API, rate-limited, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemma-4-26b-a4b-it:free
- Type: Text
- Publisher: Google
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-03
- Page: https://docs.oceantoken.ai/models/google/gemma-4-26b-a4b-it--free

### Gemma 4 31B IT (`google/gemma-4-31b-it`)

google/gemma-4-31b-it is a language model from Google you can call on the OceanToken API at $0.16 per 1M input tokens and $0.32 per 1M output tokens, with a 262K-token context window and up to 16K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemma-4-31b-it
- Type: Text
- Publisher: Google
- Context window: 262,144 tokens
- Max output: 16,384 tokens
- Input price: $0.16 per 1M tokens
- Output price: $0.32 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-02
- Page: https://docs.oceantoken.ai/models/google/gemma-4-31b-it

### Gemma 4 31B IT (Free) (`google/gemma-4-31b-it:free`)

google/gemma-4-31b-it:free is a language model from Google you can call free of charge on the OceanToken API, rate-limited, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: google/gemma-4-31b-it:free
- Type: Text
- Publisher: Google
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-02
- Page: https://docs.oceantoken.ai/models/google/gemma-4-31b-it--free

### Veo 3.1 (`google/veo-3.1`)

google/veo-3.1 is a video generation model from Google you can call on the OceanToken API at from $0.20 per second of generated video.

- Model ID: google/veo-3.1
- Type: Video
- Publisher: Google
- Price: from $0.20 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-23
- Page: https://docs.oceantoken.ai/models/google/veo-3.1

### Veo 3.1 Fast (`google/veo-3.1-fast`)

google/veo-3.1-fast is a video generation model from Google you can call on the OceanToken API at from $0.08 per second of generated video.

- Model ID: google/veo-3.1-fast
- Type: Video
- Publisher: Google
- Price: from $0.08 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-24
- Page: https://docs.oceantoken.ai/models/google/veo-3.1-fast

### Veo 3.1 Lite (`google/veo-3.1-lite`)

google/veo-3.1-lite is a video generation model from Google you can call on the OceanToken API at from $0.03 per second of generated video.

- Model ID: google/veo-3.1-lite
- Type: Video
- Publisher: Google
- Price: from $0.03 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-23
- Page: https://docs.oceantoken.ai/models/google/veo-3.1-lite

## Gryphe models

Index: https://docs.oceantoken.ai/models/gryphe

### Mythomax L2 13B (`gryphe/mythomax-l2-13b`)

gryphe/mythomax-l2-13b is a language model from Gryphe you can call on the OceanToken API at $0.35 per 1M input tokens and $0.60 per 1M output tokens, with a 8K-token context window and up to 4K output tokens.

- Model ID: gryphe/mythomax-l2-13b
- Type: Text
- Publisher: Gryphe
- Context window: 8,192 tokens
- Max output: 3,686 tokens
- Input price: $0.35 per 1M tokens
- Output price: $0.60 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2023-07-02
- Page: https://docs.oceantoken.ai/models/gryphe/mythomax-l2-13b

## Hexgrad models

Index: https://docs.oceantoken.ai/models/hexgrad

### Kokoro 82M (`hexgrad/kokoro-82m`)

hexgrad/kokoro-82m is a text-to-speech model from Hexgrad you can call on the OceanToken API at $0.00062 per 1,000 characters.

- Model ID: hexgrad/kokoro-82m
- Type: Speech
- Publisher: Hexgrad
- Price: $0.00062 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-23
- Page: https://docs.oceantoken.ai/models/hexgrad/kokoro-82m

## Heygen models

Index: https://docs.oceantoken.ai/models/heygen

### Avatar Iv (`heygen/avatar-iv`)

heygen/avatar-iv is a video generation model from Heygen you can call on the OceanToken API at from $0.05 per second of generated video.

- Model ID: heygen/avatar-iv
- Type: Video
- Publisher: Heygen
- Price: from $0.05 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-24
- Page: https://docs.oceantoken.ai/models/heygen/avatar-iv

## IBM Granite models

Index: https://docs.oceantoken.ai/models/ibm-granite

### Granite 4.0 H Micro (`ibm-granite/granite-4.0-h-micro`)

ibm-granite/granite-4.0-h-micro is a language model from IBM Granite you can call on the OceanToken API at $0.017 per 1M input tokens and $0.112 per 1M output tokens, with a 131K-token context window and up to 118K output tokens.

- Model ID: ibm-granite/granite-4.0-h-micro
- Type: Text
- Publisher: IBM Granite
- Context window: 131,000 tokens
- Max output: 117,900 tokens
- Input price: $0.017 per 1M tokens
- Output price: $0.112 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-20
- Page: https://docs.oceantoken.ai/models/ibm-granite/granite-4.0-h-micro

### Granite 4.2 8B (`ibm-granite/granite-4.2-8b`)

ibm-granite/granite-4.2-8b is a language model from IBM Granite you can call on the OceanToken API at $0.06 per 1M input tokens and $0.25 per 1M output tokens, with a 131K-token context window and up to 118K output tokens; it supports reasoning, tool calling.

- Model ID: ibm-granite/granite-4.2-8b
- Type: Text
- Publisher: IBM Granite
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.06 per 1M tokens
- Output price: $0.25 per 1M tokens
- Cached input price: $0.015 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-31
- Page: https://docs.oceantoken.ai/models/ibm-granite/granite-4.2-8b

## Inception models

Index: https://docs.oceantoken.ai/models/inception

### Mercury 2 (`inception/mercury-2`)

inception/mercury-2 is a language model from Inception you can call on the OceanToken API at $0.25 per 1M input tokens and $0.75 per 1M output tokens, with a 128K-token context window and up to 50K output tokens; it supports reasoning, tool calling.

- Model ID: inception/mercury-2
- Type: Text
- Publisher: Inception
- Context window: 128,000 tokens
- Max output: 50,000 tokens
- Input price: $0.25 per 1M tokens
- Output price: $0.75 per 1M tokens
- Cached input price: $0.025 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-04
- Page: https://docs.oceantoken.ai/models/inception/mercury-2

### Mercury 2.5 (`inception/mercury-2.5`)

inception/mercury-2.5 is a language model from Inception you can call on the OceanToken API at $0.04 per 1M input tokens and $0.15 per 1M output tokens, with a 260K-token context window and up to 66K output tokens; it supports reasoning, tool calling.

- Model ID: inception/mercury-2.5
- Type: Text
- Publisher: Inception
- Context window: 260,000 tokens
- Max output: 65,536 tokens
- Input price: $0.04 per 1M tokens
- Output price: $0.15 per 1M tokens
- Cached input price: $0.004 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-08
- Page: https://docs.oceantoken.ai/models/inception/mercury-2.5

## inclusionAI models

Index: https://docs.oceantoken.ai/models/inclusionai

### Ling-3.0 Flash (`inclusionai/ling-3.0-flash`)

inclusionai/ling-3.0-flash is a language model from inclusionAI you can call on the OceanToken API at $0.021 per 1M input tokens and $0.063 per 1M output tokens, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: inclusionai/ling-3.0-flash
- Type: Text
- Publisher: inclusionAI
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Input price: $0.021 per 1M tokens
- Output price: $0.063 per 1M tokens
- Cached input price: $0.0042 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-23
- Page: https://docs.oceantoken.ai/models/inclusionai/ling-3.0-flash

### Ling-3.0 Flash VL (`inclusionai/ling-3.0-flash-vl`)

inclusionai/ling-3.0-flash-vl is a language model from inclusionAI you can call on the OceanToken API at $0.06 per 1M input tokens and $0.18 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: inclusionai/ling-3.0-flash-vl
- Type: Text
- Publisher: inclusionAI
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $0.06 per 1M tokens
- Output price: $0.18 per 1M tokens
- Cached input price: $0.012 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-10
- Page: https://docs.oceantoken.ai/models/inclusionai/ling-3.0-flash-vl

## Inference.net models

Index: https://docs.oceantoken.ai/models/inference-net

### Schematron V2 Small (`inference-net/schematron-v2-small`)

inference-net/schematron-v2-small is a language model from Inference.net you can call on the OceanToken API at $0.05 per 1M input tokens and $0.23 per 1M output tokens, with a 128K-token context window and up to 4K output tokens.

- Model ID: inference-net/schematron-v2-small
- Type: Text
- Publisher: Inference.net
- Context window: 128,000 tokens
- Max output: 4,096 tokens
- Input price: $0.05 per 1M tokens
- Output price: $0.23 per 1M tokens
- Cached input price: $0.05 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-12
- Page: https://docs.oceantoken.ai/models/inference-net/schematron-v2-small

### Schematron V2 Turbo (`inference-net/schematron-v2-turbo`)

inference-net/schematron-v2-turbo is a language model from Inference.net you can call on the OceanToken API at $0.03 per 1M input tokens and $0.15 per 1M output tokens, with a 128K-token context window and up to 8K output tokens.

- Model ID: inference-net/schematron-v2-turbo
- Type: Text
- Publisher: Inference.net
- Context window: 128,000 tokens
- Max output: 8,192 tokens
- Input price: $0.03 per 1M tokens
- Output price: $0.15 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-12
- Page: https://docs.oceantoken.ai/models/inference-net/schematron-v2-turbo

## intfloat models

Index: https://docs.oceantoken.ai/models/intfloat

### E5 Base V2 (`intfloat/e5-base-v2`)

intfloat/e5-base-v2 is a text embedding model from intfloat you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: intfloat/e5-base-v2
- Type: Embeddings
- Publisher: intfloat
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/intfloat/e5-base-v2

### E5 Large V2 (`intfloat/e5-large-v2`)

intfloat/e5-large-v2 is a text embedding model from intfloat you can call on the OceanToken API at $0.01 per 1M input tokens, with a 1K-token context window.

- Model ID: intfloat/e5-large-v2
- Type: Embeddings
- Publisher: intfloat
- Context window: 512 tokens
- Input price: $0.01 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/intfloat/e5-large-v2

### Multilingual E5 Large (`intfloat/multilingual-e5-large`)

intfloat/multilingual-e5-large is a text embedding model from intfloat you can call on the OceanToken API at $0.01 per 1M input tokens, with a 1K-token context window.

- Model ID: intfloat/multilingual-e5-large
- Type: Embeddings
- Publisher: intfloat
- Context window: 512 tokens
- Input price: $0.01 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/intfloat/multilingual-e5-large

## Krea models

Index: https://docs.oceantoken.ai/models/krea

### Krea 2 Large (`krea/krea-2-large`)

krea/krea-2-large is an image generation model from Krea you can call on the OceanToken API at $0.06 per generated image; it supports image input.

- Model ID: krea/krea-2-large
- Type: Image
- Publisher: Krea
- Price: $0.06 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-20
- Page: https://docs.oceantoken.ai/models/krea/krea-2-large

### Krea 2 Medium (`krea/krea-2-medium`)

krea/krea-2-medium is an image generation model from Krea you can call on the OceanToken API at $0.03 per generated image; it supports image input.

- Model ID: krea/krea-2-medium
- Type: Image
- Publisher: Krea
- Price: $0.03 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-20
- Page: https://docs.oceantoken.ai/models/krea/krea-2-medium

### Krea 2 Medium Turbo (`krea/krea-2-medium-turbo`)

krea/krea-2-medium-turbo is an image generation model from Krea you can call on the OceanToken API at $0.015 per generated image; it supports image input.

- Model ID: krea/krea-2-medium-turbo
- Type: Image
- Publisher: Krea
- Price: $0.015 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-20
- Page: https://docs.oceantoken.ai/models/krea/krea-2-medium-turbo

## Kuaishou models

Index: https://docs.oceantoken.ai/models/kwaivgi

### Kling V3.0 Pro (`kwaivgi/kling-v3.0-pro`)

kwaivgi/kling-v3.0-pro is a video generation model from Kuaishou you can call on the OceanToken API at from $0.112 per second of generated video.

- Model ID: kwaivgi/kling-v3.0-pro
- Type: Video
- Publisher: Kuaishou
- Price: from $0.112 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-29
- Page: https://docs.oceantoken.ai/models/kwaivgi/kling-v3.0-pro

### Kling V3.0 Std (`kwaivgi/kling-v3.0-std`)

kwaivgi/kling-v3.0-std is a video generation model from Kuaishou you can call on the OceanToken API at from $0.084 per second of generated video.

- Model ID: kwaivgi/kling-v3.0-std
- Type: Video
- Publisher: Kuaishou
- Price: from $0.084 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-29
- Page: https://docs.oceantoken.ai/models/kwaivgi/kling-v3.0-std

### Kling Video o1 (`kwaivgi/kling-video-o1`)

kwaivgi/kling-video-o1 is a video generation model from Kuaishou you can call on the OceanToken API at from $0.112 per second of generated video.

- Model ID: kwaivgi/kling-video-o1
- Type: Video
- Publisher: Kuaishou
- Price: from $0.112 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-20
- Page: https://docs.oceantoken.ai/models/kwaivgi/kling-video-o1

## Liquid AI models

Index: https://docs.oceantoken.ai/models/liquid

### LFM 2.5 2.6b (Free) (`liquid/lfm-2.5-2.6b:free`)

liquid/lfm-2.5-2.6b:free is a language model from Liquid AI you can call free of charge on the OceanToken API, rate-limited, with a 66K-token context window and up to 8K output tokens; it supports reasoning, tool calling.

- Model ID: liquid/lfm-2.5-2.6b:free
- Type: Text
- Publisher: Liquid AI
- Context window: 65,536 tokens
- Max output: 8,192 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-11
- Page: https://docs.oceantoken.ai/models/liquid/lfm-2.5-2.6b--free

### LFM 2.5 Embedding 350M (Free) (`liquid/lfm-2.5-embedding-350m:free`)

liquid/lfm-2.5-embedding-350m:free is a text embedding model from Liquid AI you can call free of charge on the OceanToken API, rate-limited, with a 1K-token context window.

- Model ID: liquid/lfm-2.5-embedding-350m:free
- Type: Embeddings
- Publisher: Liquid AI
- Context window: 512 tokens
- Price: Free, rate-limited
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-18
- Page: https://docs.oceantoken.ai/models/liquid/lfm-2.5-embedding-350m--free

## Mancer models

Index: https://docs.oceantoken.ai/models/mancer

### Weaver (`mancer/weaver`)

mancer/weaver is a language model from Mancer you can call on the OceanToken API at $0.40 per 1M input tokens and $0.75 per 1M output tokens, with a 8K-token context window and up to 6K output tokens.

- Model ID: mancer/weaver
- Type: Text
- Publisher: Mancer
- Context window: 8,000 tokens
- Max output: 6,000 tokens
- Input price: $0.40 per 1M tokens
- Output price: $0.75 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2023-08-02
- Page: https://docs.oceantoken.ai/models/mancer/weaver

## Meituan models

Index: https://docs.oceantoken.ai/models/meituan

### Longcat 2.0 (`meituan/longcat-2.0`)

meituan/longcat-2.0 is a language model from Meituan you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 1.05M-token context window and up to 262K output tokens; it supports reasoning, tool calling.

- Model ID: meituan/longcat-2.0
- Type: Text
- Publisher: Meituan
- Context window: 1,048,756 tokens
- Max output: 262,144 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.006 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-20
- Page: https://docs.oceantoken.ai/models/meituan/longcat-2.0

## Meta models

Index: https://docs.oceantoken.ai/models/meta

### Muse Glimmer 30B (`meta/muse-glimmer-30b`)

meta/muse-glimmer-30b is a language model from Meta you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 131K-token context window and up to 16K output tokens; it supports reasoning, tool calling, image input.

- Model ID: meta/muse-glimmer-30b
- Type: Text
- Publisher: Meta
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.04 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-09
- Page: https://docs.oceantoken.ai/models/meta/muse-glimmer-30b

### Muse Spark 1.1 (`meta/muse-spark-1.1`)

meta/muse-spark-1.1 is a language model from Meta you can call on the OceanToken API at $1.25 per 1M input tokens and $4.25 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: meta/muse-spark-1.1
- Type: Text
- Publisher: Meta
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $1.25 per 1M tokens
- Output price: $4.25 per 1M tokens
- Cached input price: $0.15 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-16
- Page: https://docs.oceantoken.ai/models/meta/muse-spark-1.1

### Muse Spark 1.2 (`meta/muse-spark-1.2`)

meta/muse-spark-1.2 is a language model from Meta you can call on the OceanToken API at $1.25 per 1M input tokens and $4.25 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: meta/muse-spark-1.2
- Type: Text
- Publisher: Meta
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $1.25 per 1M tokens
- Output price: $4.25 per 1M tokens
- Cached input price: $0.15 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-05
- Page: https://docs.oceantoken.ai/models/meta/muse-spark-1.2

### Muse Spark 1.3 (`meta/muse-spark-1.3`)

meta/muse-spark-1.3 is a language model from Meta you can call on the OceanToken API at $1.25 per 1M input tokens and $4.25 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: meta/muse-spark-1.3
- Type: Text
- Publisher: Meta
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $1.25 per 1M tokens
- Output price: $4.25 per 1M tokens
- Cached input price: $0.15 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-02
- Page: https://docs.oceantoken.ai/models/meta/muse-spark-1.3

### Muse Voice Transcribe 1.0 (`meta/muse-voice-transcribe-1.0`)

meta/muse-voice-transcribe-1.0 is a speech-to-text model from Meta you can call on the OceanToken API at $0.003 per minute of audio.

- Model ID: meta/muse-voice-transcribe-1.0
- Type: Transcription
- Publisher: Meta
- Price: $0.003 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-11
- Page: https://docs.oceantoken.ai/models/meta/muse-voice-transcribe-1.0

## Meta models

Index: https://docs.oceantoken.ai/models/meta-llama

### Llama 3.1 70B Instruct (`meta-llama/llama-3.1-70b-instruct`)

meta-llama/llama-3.1-70b-instruct is a language model from Meta you can call on the OceanToken API at $0.40 per 1M input tokens and $0.40 per 1M output tokens, with a 131K-token context window and up to 16K output tokens; it supports tool calling.

- Model ID: meta-llama/llama-3.1-70b-instruct
- Type: Text
- Publisher: Meta
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.40 per 1M tokens
- Output price: $0.40 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-07-23
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-3.1-70b-instruct

### Llama 3.1 8B Instruct (`meta-llama/llama-3.1-8b-instruct`)

meta-llama/llama-3.1-8b-instruct is a language model from Meta you can call on the OceanToken API at $0.05 per 1M input tokens and $0.08 per 1M output tokens, with a 131K-token context window and up to 118K output tokens; it supports tool calling.

- Model ID: meta-llama/llama-3.1-8b-instruct
- Type: Text
- Publisher: Meta
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.05 per 1M tokens
- Output price: $0.08 per 1M tokens
- Cached input price: $0.025 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-07-23
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-3.1-8b-instruct

### Llama 3.2 1B Instruct (`meta-llama/llama-3.2-1b-instruct`)

meta-llama/llama-3.2-1b-instruct is a language model from Meta you can call on the OceanToken API at $0.027 per 1M input tokens and $0.201 per 1M output tokens, with a 60K-token context window and up to 54K output tokens.

- Model ID: meta-llama/llama-3.2-1b-instruct
- Type: Text
- Publisher: Meta
- Context window: 60,000 tokens
- Max output: 54,000 tokens
- Input price: $0.027 per 1M tokens
- Output price: $0.201 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-09-25
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-3.2-1b-instruct

### Llama 3.2 3B Instruct (`meta-llama/llama-3.2-3b-instruct`)

meta-llama/llama-3.2-3b-instruct is a language model from Meta you can call on the OceanToken API at $0.05 per 1M input tokens and $0.33 per 1M output tokens, with a 131K-token context window and up to 118K output tokens.

- Model ID: meta-llama/llama-3.2-3b-instruct
- Type: Text
- Publisher: Meta
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.05 per 1M tokens
- Output price: $0.33 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-09-25
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-3.2-3b-instruct

### Llama 3.3 70B Instruct (`meta-llama/llama-3.3-70b-instruct`)

meta-llama/llama-3.3-70b-instruct is a language model from Meta you can call on the OceanToken API at $0.45 per 1M input tokens and $0.90 per 1M output tokens, with a 131K-token context window and up to 16K output tokens; it supports tool calling.

- Model ID: meta-llama/llama-3.3-70b-instruct
- Type: Text
- Publisher: Meta
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.45 per 1M tokens
- Output price: $0.90 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-06
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-3.3-70b-instruct

### Llama 4 Maverick (`meta-llama/llama-4-maverick`)

meta-llama/llama-4-maverick is a language model from Meta you can call on the OceanToken API at $0.27 per 1M input tokens and $0.85 per 1M output tokens, with a 1.05M-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: meta-llama/llama-4-maverick
- Type: Text
- Publisher: Meta
- Context window: 1,048,576 tokens
- Max output: 16,384 tokens
- Input price: $0.27 per 1M tokens
- Output price: $0.85 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-05
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-4-maverick

### Llama 4 Scout (`meta-llama/llama-4-scout`)

meta-llama/llama-4-scout is a language model from Meta you can call on the OceanToken API at $0.15 per 1M input tokens and $0.45 per 1M output tokens, with a 1.31M-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: meta-llama/llama-4-scout
- Type: Text
- Publisher: Meta
- Context window: 1,310,720 tokens
- Max output: 16,384 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.45 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-05
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-4-scout

### Llama Guard 4 12B (`meta-llama/llama-guard-4-12b`)

meta-llama/llama-guard-4-12b is a language model from Meta you can call on the OceanToken API at $0.18 per 1M input tokens and $0.18 per 1M output tokens, with a 164K-token context window and up to 16K output tokens; it supports image input.

- Model ID: meta-llama/llama-guard-4-12b
- Type: Text
- Publisher: Meta
- Context window: 163,840 tokens
- Max output: 16,384 tokens
- Input price: $0.18 per 1M tokens
- Output price: $0.18 per 1M tokens
- Capabilities: image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-30
- Page: https://docs.oceantoken.ai/models/meta-llama/llama-guard-4-12b

## Microsoft models

Index: https://docs.oceantoken.ai/models/microsoft

### Mai Image 2.5 (`microsoft/mai-image-2.5`)

microsoft/mai-image-2.5 is an image generation model from Microsoft you can call on the OceanToken API at $5.00 per 1M input tokens and $47.00 per 1M output tokens; it supports image input.

- Model ID: microsoft/mai-image-2.5
- Type: Image
- Publisher: Microsoft
- Input price: $5.00 per 1M tokens
- Output price: $47.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-02
- Page: https://docs.oceantoken.ai/models/microsoft/mai-image-2.5

### Mai Image 2.5 Pro (`microsoft/mai-image-2.5-pro`)

microsoft/mai-image-2.5-pro is an image generation model from Microsoft you can call on the OceanToken API at $5.00 per 1M input tokens and $108.00 per 1M output tokens; it supports image input.

- Model ID: microsoft/mai-image-2.5-pro
- Type: Image
- Publisher: Microsoft
- Input price: $5.00 per 1M tokens
- Output price: $108.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-23
- Page: https://docs.oceantoken.ai/models/microsoft/mai-image-2.5-pro

### Mai Image 2.6 (`microsoft/mai-image-2.6`)

microsoft/mai-image-2.6 is an image generation model from Microsoft you can call on the OceanToken API at $5.00 per 1M input tokens and $38.00 per 1M output tokens; it supports image input.

- Model ID: microsoft/mai-image-2.6
- Type: Image
- Publisher: Microsoft
- Input price: $5.00 per 1M tokens
- Output price: $38.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-04
- Page: https://docs.oceantoken.ai/models/microsoft/mai-image-2.6

### Mai Image 2.6 Flash (`microsoft/mai-image-2.6-flash`)

microsoft/mai-image-2.6-flash is an image generation model from Microsoft you can call on the OceanToken API at $1.75 per 1M input tokens and $19.00 per 1M output tokens; it supports image input.

- Model ID: microsoft/mai-image-2.6-flash
- Type: Image
- Publisher: Microsoft
- Input price: $1.75 per 1M tokens
- Output price: $19.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-04
- Page: https://docs.oceantoken.ai/models/microsoft/mai-image-2.6-flash

### Mai Transcribe 1.5 (`microsoft/mai-transcribe-1.5`)

microsoft/mai-transcribe-1.5 is a speech-to-text model from Microsoft you can call on the OceanToken API at $21.60 per minute of audio.

- Model ID: microsoft/mai-transcribe-1.5
- Type: Transcription
- Publisher: Microsoft
- Price: $21.60 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-02
- Page: https://docs.oceantoken.ai/models/microsoft/mai-transcribe-1.5

### Mai Transcribe 2 (`microsoft/mai-transcribe-2`)

microsoft/mai-transcribe-2 is a speech-to-text model from Microsoft you can call on the OceanToken API at $6.00 per minute of audio.

- Model ID: microsoft/mai-transcribe-2
- Type: Transcription
- Publisher: Microsoft
- Price: $6.00 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-03
- Page: https://docs.oceantoken.ai/models/microsoft/mai-transcribe-2

### Mai Voice 2 (`microsoft/mai-voice-2`)

microsoft/mai-voice-2 is a text-to-speech model from Microsoft you can call on the OceanToken API at $0.022 per 1,000 characters.

- Model ID: microsoft/mai-voice-2
- Type: Speech
- Publisher: Microsoft
- Price: $0.022 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-02
- Page: https://docs.oceantoken.ai/models/microsoft/mai-voice-2

### Mai Voice 2 Flash (`microsoft/mai-voice-2-flash`)

microsoft/mai-voice-2-flash is a text-to-speech model from Microsoft you can call on the OceanToken API at $0.015 per 1,000 characters.

- Model ID: microsoft/mai-voice-2-flash
- Type: Speech
- Publisher: Microsoft
- Price: $0.015 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-23
- Page: https://docs.oceantoken.ai/models/microsoft/mai-voice-2-flash

### Phi-4 (`microsoft/phi-4`)

microsoft/phi-4 is a language model from Microsoft you can call on the OceanToken API at $0.056 per 1M input tokens and $0.112 per 1M output tokens, with a 16K-token context window and up to 15K output tokens.

- Model ID: microsoft/phi-4
- Type: Text
- Publisher: Microsoft
- Context window: 16,384 tokens
- Max output: 14,745 tokens
- Input price: $0.056 per 1M tokens
- Output price: $0.112 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-01-10
- Page: https://docs.oceantoken.ai/models/microsoft/phi-4

### Wizardlm 2 8x22b (`microsoft/wizardlm-2-8x22b`)

microsoft/wizardlm-2-8x22b is a language model from Microsoft you can call on the OceanToken API at $0.62 per 1M input tokens and $0.62 per 1M output tokens, with a 66K-token context window and up to 8K output tokens.

- Model ID: microsoft/wizardlm-2-8x22b
- Type: Text
- Publisher: Microsoft
- Context window: 65,535 tokens
- Max output: 8,000 tokens
- Input price: $0.62 per 1M tokens
- Output price: $0.62 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-04-16
- Page: https://docs.oceantoken.ai/models/microsoft/wizardlm-2-8x22b

## MiniMax models

Index: https://docs.oceantoken.ai/models/minimax

### Hailuo 2.3 (`minimax/hailuo-2.3`)

minimax/hailuo-2.3 is a video generation model from MiniMax you can call on the OceanToken API at from $0.0817 per second of generated video.

- Model ID: minimax/hailuo-2.3
- Type: Video
- Publisher: MiniMax
- Price: from $0.0817 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-20
- Page: https://docs.oceantoken.ai/models/minimax/hailuo-2.3

### Hailuo 3 (`minimax/hailuo-3`)

minimax/hailuo-3 is a video generation model from MiniMax you can call on the OceanToken API at from $0.08 per second of generated video.

- Model ID: minimax/hailuo-3
- Type: Video
- Publisher: MiniMax
- Price: from $0.08 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/minimax/hailuo-3

### Hailuo 3 Max (`minimax/hailuo-3-max`)

minimax/hailuo-3-max is a video generation model from MiniMax you can call on the OceanToken API at from $0.05 per second of generated video.

- Model ID: minimax/hailuo-3-max
- Type: Video
- Publisher: MiniMax
- Price: from $0.05 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-02
- Page: https://docs.oceantoken.ai/models/minimax/hailuo-3-max

### MiniMax 01 (`minimax/minimax-01`)

minimax/minimax-01 is a language model from MiniMax you can call on the OceanToken API at $0.20 per 1M input tokens and $1.10 per 1M output tokens, with a 1M-token context window and up to 40K output tokens; it supports image input.

- Model ID: minimax/minimax-01
- Type: Text
- Publisher: MiniMax
- Context window: 1,000,192 tokens
- Max output: 40,000 tokens
- Input price: $0.20 per 1M tokens
- Output price: $1.10 per 1M tokens
- Capabilities: image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-01-15
- Page: https://docs.oceantoken.ai/models/minimax/minimax-01

### MiniMax M1 (`minimax/minimax-m1`)

minimax/minimax-m1 is a language model from MiniMax you can call on the OceanToken API at $0.40 per 1M input tokens and $2.20 per 1M output tokens, with a 1M-token context window and up to 40K output tokens; it supports reasoning, tool calling.

- Model ID: minimax/minimax-m1
- Type: Text
- Publisher: MiniMax
- Context window: 1,000,000 tokens
- Max output: 40,000 tokens
- Input price: $0.40 per 1M tokens
- Output price: $2.20 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-06-17
- Page: https://docs.oceantoken.ai/models/minimax/minimax-m1

### MiniMax M2 (`minimax/minimax-m2`)

minimax/minimax-m2 is a language model from MiniMax you can call on the OceanToken API at $0.255 per 1M input tokens and $1.02 per 1M output tokens, with a 205K-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: minimax/minimax-m2
- Type: Text
- Publisher: MiniMax
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Input price: $0.255 per 1M tokens
- Output price: $1.02 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-23
- Page: https://docs.oceantoken.ai/models/minimax/minimax-m2

### MiniMax M2 Her (`minimax/minimax-m2-her`)

minimax/minimax-m2-her is a language model from MiniMax you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 66K-token context window and up to 2K output tokens.

- Model ID: minimax/minimax-m2-her
- Type: Text
- Publisher: MiniMax
- Context window: 65,536 tokens
- Max output: 2,048 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-23
- Page: https://docs.oceantoken.ai/models/minimax/minimax-m2-her

### MiniMax M2.1 (`minimax/minimax-m2.1`)

minimax/minimax-m2.1 is a language model from MiniMax you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 205K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: minimax/minimax-m2.1
- Type: Text
- Publisher: MiniMax
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-23
- Page: https://docs.oceantoken.ai/models/minimax/minimax-m2.1

### MiniMax M2.5 (`minimax/minimax-m2.5`)

minimax/minimax-m2.5 is a language model from MiniMax you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 205K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: minimax/minimax-m2.5
- Type: Text
- Publisher: MiniMax
- Context window: 204,800 tokens
- Max output: 32,768 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-12
- Page: https://docs.oceantoken.ai/models/minimax/minimax-m2.5

### MiniMax M2.7 (`minimax/minimax-m2.7`)

minimax/minimax-m2.7 is a language model from MiniMax you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 205K-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: minimax/minimax-m2.7
- Type: Text
- Publisher: MiniMax
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.06 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-18
- Page: https://docs.oceantoken.ai/models/minimax/minimax-m2.7

### MiniMax M3 (`minimax/minimax-m3`)

minimax/minimax-m3 is a language model from MiniMax you can call on the OceanToken API at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 524K-token context window and up to 512K output tokens; it supports reasoning, tool calling, image input.

- Model ID: minimax/minimax-m3
- Type: Text
- Publisher: MiniMax
- Context window: 524,288 tokens
- Max output: 512,000 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.06 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-31
- Page: https://docs.oceantoken.ai/models/minimax/minimax-m3

### Speech 2.8 HD (`minimax/speech-2.8-hd`)

minimax/speech-2.8-hd is a text-to-speech model from MiniMax you can call on the OceanToken API at $0.10 per 1,000 characters.

- Model ID: minimax/speech-2.8-hd
- Type: Speech
- Publisher: MiniMax
- Price: $0.10 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-16
- Page: https://docs.oceantoken.ai/models/minimax/speech-2.8-hd

### Speech 2.8 Turbo (`minimax/speech-2.8-turbo`)

minimax/speech-2.8-turbo is a text-to-speech model from MiniMax you can call on the OceanToken API at $0.06 per 1,000 characters.

- Model ID: minimax/speech-2.8-turbo
- Type: Speech
- Publisher: MiniMax
- Price: $0.06 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-16
- Page: https://docs.oceantoken.ai/models/minimax/speech-2.8-turbo

## Mistral AI models

Index: https://docs.oceantoken.ai/models/mistralai

### Codestral 2508 (`mistralai/codestral-2508`)

mistralai/codestral-2508 is a language model from Mistral AI you can call on the OceanToken API at $0.30 per 1M input tokens and $0.90 per 1M output tokens, with a 256K-token context window and up to 205K output tokens; it supports tool calling.

- Model ID: mistralai/codestral-2508
- Type: Text
- Publisher: Mistral AI
- Context window: 256,000 tokens
- Max output: 204,800 tokens
- Input price: $0.30 per 1M tokens
- Output price: $0.90 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-01
- Page: https://docs.oceantoken.ai/models/mistralai/codestral-2508

### Codestral Embed 2505 (`mistralai/codestral-embed-2505`)

mistralai/codestral-embed-2505 is a text embedding model from Mistral AI you can call on the OceanToken API at $0.15 per 1M input tokens, with a 8K-token context window.

- Model ID: mistralai/codestral-embed-2505
- Type: Embeddings
- Publisher: Mistral AI
- Context window: 8,192 tokens
- Input price: $0.15 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-30
- Page: https://docs.oceantoken.ai/models/mistralai/codestral-embed-2505

### Devstral 2512 (`mistralai/devstral-2512`)

mistralai/devstral-2512 is a language model from Mistral AI you can call on the OceanToken API at $0.40 per 1M input tokens and $2.00 per 1M output tokens, with a 262K-token context window and up to 210K output tokens; it supports tool calling.

- Model ID: mistralai/devstral-2512
- Type: Text
- Publisher: Mistral AI
- Context window: 262,144 tokens
- Max output: 209,715 tokens
- Input price: $0.40 per 1M tokens
- Output price: $2.00 per 1M tokens
- Cached input price: $0.04 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-09
- Page: https://docs.oceantoken.ai/models/mistralai/devstral-2512

### Ministral 14B 2512 (`mistralai/ministral-14b-2512`)

mistralai/ministral-14b-2512 is a language model from Mistral AI you can call on the OceanToken API at $0.20 per 1M input tokens and $0.20 per 1M output tokens, with a 262K-token context window and up to 210K output tokens; it supports tool calling, image input.

- Model ID: mistralai/ministral-14b-2512
- Type: Text
- Publisher: Mistral AI
- Context window: 262,144 tokens
- Max output: 209,715 tokens
- Input price: $0.20 per 1M tokens
- Output price: $0.20 per 1M tokens
- Cached input price: $0.02 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-02
- Page: https://docs.oceantoken.ai/models/mistralai/ministral-14b-2512

### Ministral 3B 2512 (`mistralai/ministral-3b-2512`)

mistralai/ministral-3b-2512 is a language model from Mistral AI you can call on the OceanToken API at $0.10 per 1M input tokens and $0.10 per 1M output tokens, with a 131K-token context window and up to 105K output tokens; it supports tool calling, image input.

- Model ID: mistralai/ministral-3b-2512
- Type: Text
- Publisher: Mistral AI
- Context window: 131,072 tokens
- Max output: 104,857 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.10 per 1M tokens
- Cached input price: $0.01 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-02
- Page: https://docs.oceantoken.ai/models/mistralai/ministral-3b-2512

### Ministral 8B 2512 (`mistralai/ministral-8b-2512`)

mistralai/ministral-8b-2512 is a language model from Mistral AI you can call on the OceanToken API at $0.15 per 1M input tokens and $0.15 per 1M output tokens, with a 262K-token context window and up to 210K output tokens; it supports tool calling, image input.

- Model ID: mistralai/ministral-8b-2512
- Type: Text
- Publisher: Mistral AI
- Context window: 262,144 tokens
- Max output: 209,715 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.15 per 1M tokens
- Cached input price: $0.015 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-02
- Page: https://docs.oceantoken.ai/models/mistralai/ministral-8b-2512

### Mistral Embed 2312 (`mistralai/mistral-embed-2312`)

mistralai/mistral-embed-2312 is a text embedding model from Mistral AI you can call on the OceanToken API at $0.10 per 1M input tokens, with a 8K-token context window.

- Model ID: mistralai/mistral-embed-2312
- Type: Embeddings
- Publisher: Mistral AI
- Context window: 8,192 tokens
- Input price: $0.10 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-31
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-embed-2312

### Mistral Large (`mistralai/mistral-large`)

mistralai/mistral-large is a language model from Mistral AI you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 128K-token context window and up to 102K output tokens; it supports tool calling.

- Model ID: mistralai/mistral-large
- Type: Text
- Publisher: Mistral AI
- Context window: 128,000 tokens
- Max output: 102,400 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-02-26
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-large

### Mistral Large 2407 (`mistralai/mistral-large-2407`)

mistralai/mistral-large-2407 is a language model from Mistral AI you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 131K-token context window and up to 105K output tokens; it supports tool calling.

- Model ID: mistralai/mistral-large-2407
- Type: Text
- Publisher: Mistral AI
- Context window: 131,072 tokens
- Max output: 104,857 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-11-19
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-large-2407

### Mistral Medium 3 (`mistralai/mistral-medium-3`)

mistralai/mistral-medium-3 is a language model from Mistral AI you can call on the OceanToken API at $0.40 per 1M input tokens and $2.00 per 1M output tokens, with a 131K-token context window and up to 105K output tokens; it supports tool calling, image input.

- Model ID: mistralai/mistral-medium-3
- Type: Text
- Publisher: Mistral AI
- Context window: 131,072 tokens
- Max output: 104,857 tokens
- Input price: $0.40 per 1M tokens
- Output price: $2.00 per 1M tokens
- Cached input price: $0.04 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-05-07
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-medium-3

### Mistral Medium 3.5 (`mistralai/mistral-medium-3-5`)

mistralai/mistral-medium-3-5 is a language model from Mistral AI you can call on the OceanToken API at $1.50 per 1M input tokens and $7.50 per 1M output tokens, with a 262K-token context window and up to 210K output tokens; it supports reasoning, tool calling, image input.

- Model ID: mistralai/mistral-medium-3-5
- Type: Text
- Publisher: Mistral AI
- Context window: 262,144 tokens
- Max output: 209,715 tokens
- Input price: $1.50 per 1M tokens
- Output price: $7.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-30
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-medium-3-5

### Mistral Medium 3.1 (`mistralai/mistral-medium-3.1`)

mistralai/mistral-medium-3.1 is a language model from Mistral AI you can call on the OceanToken API at $0.40 per 1M input tokens and $2.00 per 1M output tokens, with a 131K-token context window and up to 105K output tokens; it supports tool calling, image input.

- Model ID: mistralai/mistral-medium-3.1
- Type: Text
- Publisher: Mistral AI
- Context window: 131,072 tokens
- Max output: 104,857 tokens
- Input price: $0.40 per 1M tokens
- Output price: $2.00 per 1M tokens
- Cached input price: $0.04 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-13
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-medium-3.1

### Mistral Nemo (`mistralai/mistral-nemo`)

mistralai/mistral-nemo is a language model from Mistral AI you can call on the OceanToken API at $0.15 per 1M input tokens and $0.15 per 1M output tokens, with a 131K-token context window and up to 16K output tokens; it supports tool calling.

- Model ID: mistralai/mistral-nemo
- Type: Text
- Publisher: Mistral AI
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.15 per 1M tokens
- Cached input price: $0.015 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-07-19
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-nemo

### Mistral Saba (`mistralai/mistral-saba`)

mistralai/mistral-saba is a language model from Mistral AI you can call on the OceanToken API at $0.20 per 1M input tokens and $0.60 per 1M output tokens, with a 33K-token context window and up to 26K output tokens; it supports tool calling.

- Model ID: mistralai/mistral-saba
- Type: Text
- Publisher: Mistral AI
- Context window: 32,768 tokens
- Max output: 26,214 tokens
- Input price: $0.20 per 1M tokens
- Output price: $0.60 per 1M tokens
- Cached input price: $0.02 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-02-17
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-saba

### Mistral Small 24B Instruct 2501 (`mistralai/mistral-small-24b-instruct-2501`)

mistralai/mistral-small-24b-instruct-2501 is a language model from Mistral AI you can call on the OceanToken API at $0.05 per 1M input tokens and $0.08 per 1M output tokens, with a 33K-token context window and up to 16K output tokens.

- Model ID: mistralai/mistral-small-24b-instruct-2501
- Type: Text
- Publisher: Mistral AI
- Context window: 32,768 tokens
- Max output: 16,384 tokens
- Input price: $0.05 per 1M tokens
- Output price: $0.08 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-01-30
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-small-24b-instruct-2501

### Mistral Small 2603 (`mistralai/mistral-small-2603`)

mistralai/mistral-small-2603 is a language model from Mistral AI you can call on the OceanToken API at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 262K-token context window and up to 210K output tokens; it supports reasoning, tool calling, image input.

- Model ID: mistralai/mistral-small-2603
- Type: Text
- Publisher: Mistral AI
- Context window: 262,144 tokens
- Max output: 209,715 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.60 per 1M tokens
- Cached input price: $0.015 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-16
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-small-2603

### Mistral Small 3.1 24B Instruct (`mistralai/mistral-small-3.1-24b-instruct`)

mistralai/mistral-small-3.1-24b-instruct is a language model from Mistral AI you can call on the OceanToken API at $0.351 per 1M input tokens and $0.555 per 1M output tokens, with a 128K-token context window and up to 102K output tokens; it supports tool calling, image input.

- Model ID: mistralai/mistral-small-3.1-24b-instruct
- Type: Text
- Publisher: Mistral AI
- Context window: 128,000 tokens
- Max output: 102,400 tokens
- Input price: $0.351 per 1M tokens
- Output price: $0.555 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-17
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-small-3.1-24b-instruct

### Mistral Small 3.2 24B Instruct (`mistralai/mistral-small-3.2-24b-instruct`)

mistralai/mistral-small-3.2-24b-instruct is a language model from Mistral AI you can call on the OceanToken API at $0.10 per 1M input tokens and $0.30 per 1M output tokens, with a 256K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: mistralai/mistral-small-3.2-24b-instruct
- Type: Text
- Publisher: Mistral AI
- Context window: 256,000 tokens
- Max output: 16,384 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.30 per 1M tokens
- Cached input price: $0.01 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-06-20
- Page: https://docs.oceantoken.ai/models/mistralai/mistral-small-3.2-24b-instruct

### Mixtral 8x22b Instruct (`mistralai/mixtral-8x22b-instruct`)

mistralai/mixtral-8x22b-instruct is a language model from Mistral AI you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 66K-token context window and up to 52K output tokens; it supports tool calling.

- Model ID: mistralai/mixtral-8x22b-instruct
- Type: Text
- Publisher: Mistral AI
- Context window: 65,536 tokens
- Max output: 52,428 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-04-17
- Page: https://docs.oceantoken.ai/models/mistralai/mixtral-8x22b-instruct

### Voxtral Mini 3B 2507 (`mistralai/voxtral-mini-3b-2507`)

mistralai/voxtral-mini-3b-2507 is a speech-to-text model from Mistral AI you can call on the OceanToken API at $0.001 per minute of audio.

- Model ID: mistralai/voxtral-mini-3b-2507
- Type: Transcription
- Publisher: Mistral AI
- Price: $0.001 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/mistralai/voxtral-mini-3b-2507

### Voxtral Mini Transcribe (`mistralai/voxtral-mini-transcribe`)

mistralai/voxtral-mini-transcribe is a speech-to-text model from Mistral AI you can call on the OceanToken API at $0.003 per minute of audio.

- Model ID: mistralai/voxtral-mini-transcribe
- Type: Transcription
- Publisher: Mistral AI
- Price: $0.003 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-15
- Page: https://docs.oceantoken.ai/models/mistralai/voxtral-mini-transcribe

### Voxtral Mini TTS 2603 (`mistralai/voxtral-mini-tts-2603`)

mistralai/voxtral-mini-tts-2603 is a text-to-speech model from Mistral AI you can call on the OceanToken API at $0.016 per 1,000 characters.

- Model ID: mistralai/voxtral-mini-tts-2603
- Type: Speech
- Publisher: Mistral AI
- Price: $0.016 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-19
- Page: https://docs.oceantoken.ai/models/mistralai/voxtral-mini-tts-2603

### Voxtral Small 24B 2507 (`mistralai/voxtral-small-24b-2507`)

mistralai/voxtral-small-24b-2507 is a language model from Mistral AI you can call on the OceanToken API at $0.10 per 1M input tokens and $0.30 per 1M output tokens, with a 33K-token context window and up to 26K output tokens; it supports tool calling.

- Model ID: mistralai/voxtral-small-24b-2507
- Type: Text
- Publisher: Mistral AI
- Context window: 32,768 tokens
- Max output: 26,214 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.30 per 1M tokens
- Cached input price: $0.01 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-30
- Page: https://docs.oceantoken.ai/models/mistralai/voxtral-small-24b-2507

### Voxtral Small 24B 2507 STT (`mistralai/voxtral-small-24b-2507-stt`)

mistralai/voxtral-small-24b-2507-stt is a speech-to-text model from Mistral AI you can call on the OceanToken API at $0.003 per minute of audio.

- Model ID: mistralai/voxtral-small-24b-2507-stt
- Type: Transcription
- Publisher: Mistral AI
- Price: $0.003 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/mistralai/voxtral-small-24b-2507-stt

## Moonshot AI models

Index: https://docs.oceantoken.ai/models/moonshotai

### Kimi K2 (`moonshotai/kimi-k2`)

moonshotai/kimi-k2 is a language model from Moonshot AI you can call on the OceanToken API at $0.57 per 1M input tokens and $2.30 per 1M output tokens, with a 131K-token context window and up to 98K output tokens; it supports tool calling.

- Model ID: moonshotai/kimi-k2
- Type: Text
- Publisher: Moonshot AI
- Context window: 131,072 tokens
- Max output: 98,304 tokens
- Input price: $0.57 per 1M tokens
- Output price: $2.30 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-11
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-k2

### Kimi K2 0905 (`moonshotai/kimi-k2-0905`)

moonshotai/kimi-k2-0905 is a language model from Moonshot AI you can call on the OceanToken API at $0.60 per 1M input tokens and $2.50 per 1M output tokens, with a 262K-token context window and up to 98K output tokens; it supports tool calling.

- Model ID: moonshotai/kimi-k2-0905
- Type: Text
- Publisher: Moonshot AI
- Context window: 262,144 tokens
- Max output: 98,304 tokens
- Input price: $0.60 per 1M tokens
- Output price: $2.50 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-04
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-k2-0905

### Kimi K2 Thinking (`moonshotai/kimi-k2-thinking`)

moonshotai/kimi-k2-thinking is a language model from Moonshot AI you can call on the OceanToken API at $0.60 per 1M input tokens and $2.50 per 1M output tokens, with a 262K-token context window and up to 98K output tokens; it supports reasoning, tool calling.

- Model ID: moonshotai/kimi-k2-thinking
- Type: Text
- Publisher: Moonshot AI
- Context window: 262,144 tokens
- Max output: 98,304 tokens
- Input price: $0.60 per 1M tokens
- Output price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-06
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-k2-thinking

### Kimi K2.5 (`moonshotai/kimi-k2.5`)

moonshotai/kimi-k2.5 is a language model from Moonshot AI you can call on the OceanToken API at $0.57 per 1M input tokens and $2.85 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: moonshotai/kimi-k2.5
- Type: Text
- Publisher: Moonshot AI
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.57 per 1M tokens
- Output price: $2.85 per 1M tokens
- Cached input price: $0.095 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-27
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-k2.5

### Kimi K2.6 (`moonshotai/kimi-k2.6`)

moonshotai/kimi-k2.6 is a language model from Moonshot AI you can call on the OceanToken API at $0.95 per 1M input tokens and $4.00 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: moonshotai/kimi-k2.6
- Type: Text
- Publisher: Moonshot AI
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.95 per 1M tokens
- Output price: $4.00 per 1M tokens
- Cached input price: $0.16 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-20
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-k2.6

### Kimi K2.7 Code (`moonshotai/kimi-k2.7-code`)

moonshotai/kimi-k2.7-code is a language model from Moonshot AI you can call on the OceanToken API at $0.95 per 1M input tokens and $4.00 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: moonshotai/kimi-k2.7-code
- Type: Text
- Publisher: Moonshot AI
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.95 per 1M tokens
- Output price: $4.00 per 1M tokens
- Cached input price: $0.19 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-12
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-k2.7-code

### Kimi K3 (`moonshotai/kimi-k3`)

moonshotai/kimi-k3 is a language model from Moonshot AI you can call on the OceanToken API at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: moonshotai/kimi-k3
- Type: Text
- Publisher: Moonshot AI
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $3.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Cached input price: $0.30 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-16
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-k3

### Kimi Latest (`moonshotai/kimi-latest`)

moonshotai/kimi-latest is a language model from Moonshot AI you can call on the OceanToken API at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: moonshotai/kimi-latest
- Type: Text
- Publisher: Moonshot AI
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $3.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Cached input price: $0.30 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: moonshotai/kimi-k3
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/moonshotai/kimi-latest

## Morph models

Index: https://docs.oceantoken.ai/models/morph

### Morph V3 Fast (`morph/morph-v3-fast`)

morph/morph-v3-fast is a language model from Morph you can call on the OceanToken API at $0.80 per 1M input tokens and $1.20 per 1M output tokens, with a 82K-token context window and up to 38K output tokens.

- Model ID: morph/morph-v3-fast
- Type: Text
- Publisher: Morph
- Context window: 81,920 tokens
- Max output: 38,000 tokens
- Input price: $0.80 per 1M tokens
- Output price: $1.20 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-07
- Page: https://docs.oceantoken.ai/models/morph/morph-v3-fast

### Morph V3 Large (`morph/morph-v3-large`)

morph/morph-v3-large is a language model from Morph you can call on the OceanToken API at $0.90 per 1M input tokens and $1.90 per 1M output tokens, with a 262K-token context window and up to 131K output tokens.

- Model ID: morph/morph-v3-large
- Type: Text
- Publisher: Morph
- Context window: 262,144 tokens
- Max output: 131,072 tokens
- Input price: $0.90 per 1M tokens
- Output price: $1.90 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-07
- Page: https://docs.oceantoken.ai/models/morph/morph-v3-large

## Nous Research models

Index: https://docs.oceantoken.ai/models/nousresearch

### Hermes 3 Llama 3.1 405B (`nousresearch/hermes-3-llama-3.1-405b`)

nousresearch/hermes-3-llama-3.1-405b is a language model from Nous Research you can call on the OceanToken API at $1.00 per 1M input tokens and $1.00 per 1M output tokens, with a 131K-token context window and up to 16K output tokens.

- Model ID: nousresearch/hermes-3-llama-3.1-405b
- Type: Text
- Publisher: Nous Research
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $1.00 per 1M tokens
- Output price: $1.00 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-08-16
- Page: https://docs.oceantoken.ai/models/nousresearch/hermes-3-llama-3.1-405b

### Hermes 3 Llama 3.1 70B (`nousresearch/hermes-3-llama-3.1-70b`)

nousresearch/hermes-3-llama-3.1-70b is a language model from Nous Research you can call on the OceanToken API at $0.70 per 1M input tokens and $0.70 per 1M output tokens, with a 131K-token context window and up to 16K output tokens.

- Model ID: nousresearch/hermes-3-llama-3.1-70b
- Type: Text
- Publisher: Nous Research
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.70 per 1M tokens
- Output price: $0.70 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-08-18
- Page: https://docs.oceantoken.ai/models/nousresearch/hermes-3-llama-3.1-70b

### Hermes 4 405B (`nousresearch/hermes-4-405b`)

nousresearch/hermes-4-405b is a language model from Nous Research you can call on the OceanToken API at $1.00 per 1M input tokens and $3.00 per 1M output tokens, with a 131K-token context window and up to 118K output tokens; it supports reasoning.

- Model ID: nousresearch/hermes-4-405b
- Type: Text
- Publisher: Nous Research
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $1.00 per 1M tokens
- Output price: $3.00 per 1M tokens
- Capabilities: reasoning
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-26
- Page: https://docs.oceantoken.ai/models/nousresearch/hermes-4-405b

## NVIDIA models

Index: https://docs.oceantoken.ai/models/nvidia

### Llama Nemotron Embed VL 1B V2 (Free) (`nvidia/llama-nemotron-embed-vl-1b-v2:free`)

nvidia/llama-nemotron-embed-vl-1b-v2:free is a text embedding model from NVIDIA you can call free of charge on the OceanToken API, rate-limited, with a 131K-token context window.

- Model ID: nvidia/llama-nemotron-embed-vl-1b-v2:free
- Type: Embeddings
- Publisher: NVIDIA
- Context window: 131,072 tokens
- Price: Free, rate-limited
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-25
- Page: https://docs.oceantoken.ai/models/nvidia/llama-nemotron-embed-vl-1b-v2--free

### Llama Nemotron Rerank VL 1B V2 (Free) (`nvidia/llama-nemotron-rerank-vl-1b-v2:free`)

nvidia/llama-nemotron-rerank-vl-1b-v2:free is a reranking model from NVIDIA you can call free of charge on the OceanToken API, rate-limited.

- Model ID: nvidia/llama-nemotron-rerank-vl-1b-v2:free
- Type: Rerank
- Publisher: NVIDIA
- Price: Free, rate-limited
- Endpoint: /v1/rerank
- API shape: Cohere rerank
- In the catalog since: 2026-06-09
- Page: https://docs.oceantoken.ai/models/nvidia/llama-nemotron-rerank-vl-1b-v2--free

### Nemotron 3 Embed 1B (Free) (`nvidia/nemotron-3-embed-1b:free`)

nvidia/nemotron-3-embed-1b:free is a text embedding model from NVIDIA you can call free of charge on the OceanToken API, rate-limited, with a 33K-token context window.

- Model ID: nvidia/nemotron-3-embed-1b:free
- Type: Embeddings
- Publisher: NVIDIA
- Context window: 32,768 tokens
- Price: Free, rate-limited
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-16
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3-embed-1b--free

### Nemotron 3 Nano 30B A3B (`nvidia/nemotron-3-nano-30b-a3b`)

nvidia/nemotron-3-nano-30b-a3b is a language model from NVIDIA you can call on the OceanToken API at $0.06 per 1M input tokens and $0.24 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling.

- Model ID: nvidia/nemotron-3-nano-30b-a3b
- Type: Text
- Publisher: NVIDIA
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.06 per 1M tokens
- Output price: $0.24 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-14
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3-nano-30b-a3b

### Nemotron 3 Nano Omni 30B A3B Reasoning (Free) (`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`)

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free is a language model from NVIDIA you can call free of charge on the OceanToken API, rate-limited, with a 256K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
- Type: Text
- Publisher: NVIDIA
- Context window: 256,000 tokens
- Max output: 65,536 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-28
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning--free

### Nemotron 3 Super 120B A12B (`nvidia/nemotron-3-super-120b-a12b`)

nvidia/nemotron-3-super-120b-a12b is a language model from NVIDIA you can call on the OceanToken API at $0.085 per 1M input tokens and $0.40 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling.

- Model ID: nvidia/nemotron-3-super-120b-a12b
- Type: Text
- Publisher: NVIDIA
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.085 per 1M tokens
- Output price: $0.40 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-11
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3-super-120b-a12b

### Nemotron 3 Super 120B A12B (Free) (`nvidia/nemotron-3-super-120b-a12b:free`)

nvidia/nemotron-3-super-120b-a12b:free is a language model from NVIDIA you can call free of charge on the OceanToken API, rate-limited, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling.

- Model ID: nvidia/nemotron-3-super-120b-a12b:free
- Type: Text
- Publisher: NVIDIA
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-11
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3-super-120b-a12b--free

### Nemotron 3 Ultra 550B A55B (`nvidia/nemotron-3-ultra-550b-a55b`)

nvidia/nemotron-3-ultra-550b-a55b is a language model from NVIDIA you can call on the OceanToken API at $0.60 per 1M input tokens and $2.40 per 1M output tokens, with a 262K-token context window and up to 183K output tokens; it supports reasoning, tool calling.

- Model ID: nvidia/nemotron-3-ultra-550b-a55b
- Type: Text
- Publisher: NVIDIA
- Context window: 262,144 tokens
- Max output: 182,520 tokens
- Input price: $0.60 per 1M tokens
- Output price: $2.40 per 1M tokens
- Cached input price: $0.12 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-04
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3-ultra-550b-a55b

### Nemotron 3 Ultra 550B A55B (Free) (`nvidia/nemotron-3-ultra-550b-a55b:free`)

nvidia/nemotron-3-ultra-550b-a55b:free is a language model from NVIDIA you can call free of charge on the OceanToken API, rate-limited, with a 1M-token context window and up to 66K output tokens; it supports reasoning, tool calling.

- Model ID: nvidia/nemotron-3-ultra-550b-a55b:free
- Type: Text
- Publisher: NVIDIA
- Context window: 1,000,000 tokens
- Max output: 65,536 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-04
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3-ultra-550b-a55b--free

### Nemotron 3.5 ASR Streaming Multilingual 0.6b (`nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b`)

nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b is a speech-to-text model from NVIDIA you can call on the OceanToken API at $0.0002 per minute of audio.

- Model ID: nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b
- Type: Transcription
- Publisher: NVIDIA
- Price: $0.0002 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b

### Nemotron 3.5 Content Safety (`nvidia/nemotron-3.5-content-safety`)

nvidia/nemotron-3.5-content-safety is a language model from NVIDIA you can call on the OceanToken API at $0.20 per 1M input tokens and $0.20 per 1M output tokens, with a 131K-token context window and up to 118K output tokens; it supports reasoning, image input.

- Model ID: nvidia/nemotron-3.5-content-safety
- Type: Text
- Publisher: NVIDIA
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.20 per 1M tokens
- Output price: $0.20 per 1M tokens
- Capabilities: reasoning, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-04
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3.5-content-safety

### Nemotron 3.5 Content Safety (Free) (`nvidia/nemotron-3.5-content-safety:free`)

nvidia/nemotron-3.5-content-safety:free is a language model from NVIDIA you can call free of charge on the OceanToken API, rate-limited, with a 128K-token context window and up to 8K output tokens; it supports reasoning, image input.

- Model ID: nvidia/nemotron-3.5-content-safety:free
- Type: Text
- Publisher: NVIDIA
- Context window: 128,000 tokens
- Max output: 8,192 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-04
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3.5-content-safety--free

### Nemotron 3.5 Lightning (`nvidia/nemotron-3.5-lightning`)

nvidia/nemotron-3.5-lightning is a language model from NVIDIA you can call on the OceanToken API at $0.06 per 1M input tokens and $0.16 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling.

- Model ID: nvidia/nemotron-3.5-lightning
- Type: Text
- Publisher: NVIDIA
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.06 per 1M tokens
- Output price: $0.16 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-11
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3.5-lightning

### Nemotron 3.5 Lightning (Free) (`nvidia/nemotron-3.5-lightning:free`)

nvidia/nemotron-3.5-lightning:free is a language model from NVIDIA you can call free of charge on the OceanToken API, rate-limited, with a 1M-token context window and up to 66K output tokens; it supports reasoning, tool calling.

- Model ID: nvidia/nemotron-3.5-lightning:free
- Type: Text
- Publisher: NVIDIA
- Context window: 1,000,000 tokens
- Max output: 65,536 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-11
- Page: https://docs.oceantoken.ai/models/nvidia/nemotron-3.5-lightning--free

### Parakeet Tdt 0.6b V3 (`nvidia/parakeet-tdt-0.6b-v3`)

nvidia/parakeet-tdt-0.6b-v3 is a speech-to-text model from NVIDIA you can call on the OceanToken API at $0.0015 per minute of audio.

- Model ID: nvidia/parakeet-tdt-0.6b-v3
- Type: Transcription
- Publisher: NVIDIA
- Price: $0.0015 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-27
- Page: https://docs.oceantoken.ai/models/nvidia/parakeet-tdt-0.6b-v3

## OpenAI models

Index: https://docs.oceantoken.ai/models/openai

### GPT-3.5 Turbo (`openai/gpt-3.5-turbo`)

openai/gpt-3.5-turbo is a language model from OpenAI you can call on the OceanToken API at $0.50 per 1M input tokens and $1.50 per 1M output tokens, with a 16K-token context window and up to 4K output tokens; it supports tool calling.

- Model ID: openai/gpt-3.5-turbo
- Type: Text
- Publisher: OpenAI
- Context window: 16,385 tokens
- Max output: 4,096 tokens
- Input price: $0.50 per 1M tokens
- Output price: $1.50 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2023-05-28
- Page: https://docs.oceantoken.ai/models/openai/gpt-3.5-turbo

### GPT-3.5 Turbo 0613 (`openai/gpt-3.5-turbo-0613`)

openai/gpt-3.5-turbo-0613 is a language model from OpenAI you can call on the OceanToken API at $1.00 per 1M input tokens and $2.00 per 1M output tokens, with a 4K-token context window and up to 4K output tokens; it supports tool calling.

- Model ID: openai/gpt-3.5-turbo-0613
- Type: Text
- Publisher: OpenAI
- Context window: 4,095 tokens
- Max output: 3,685 tokens
- Input price: $1.00 per 1M tokens
- Output price: $2.00 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-01-25
- Page: https://docs.oceantoken.ai/models/openai/gpt-3.5-turbo-0613

### GPT-3.5 Turbo 16K (`openai/gpt-3.5-turbo-16k`)

openai/gpt-3.5-turbo-16k is a language model from OpenAI you can call on the OceanToken API at $3.00 per 1M input tokens and $4.00 per 1M output tokens, with a 16K-token context window and up to 4K output tokens; it supports tool calling.

- Model ID: openai/gpt-3.5-turbo-16k
- Type: Text
- Publisher: OpenAI
- Context window: 16,385 tokens
- Max output: 4,096 tokens
- Input price: $3.00 per 1M tokens
- Output price: $4.00 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2023-08-28
- Page: https://docs.oceantoken.ai/models/openai/gpt-3.5-turbo-16k

### GPT-4 (`openai/gpt-4`)

openai/gpt-4 is a language model from OpenAI you can call on the OceanToken API at $30.00 per 1M input tokens and $60.00 per 1M output tokens, with a 8K-token context window and up to 4K output tokens; it supports tool calling.

- Model ID: openai/gpt-4
- Type: Text
- Publisher: OpenAI
- Context window: 8,191 tokens
- Max output: 4,096 tokens
- Input price: $30.00 per 1M tokens
- Output price: $60.00 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2023-05-28
- Page: https://docs.oceantoken.ai/models/openai/gpt-4

### GPT-4 Turbo (`openai/gpt-4-turbo`)

openai/gpt-4-turbo is a language model from OpenAI you can call on the OceanToken API at $10.00 per 1M input tokens and $30.00 per 1M output tokens, with a 128K-token context window and up to 4K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4-turbo
- Type: Text
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 4,096 tokens
- Input price: $10.00 per 1M tokens
- Output price: $30.00 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-04-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-4-turbo

### GPT-4.1 (`openai/gpt-4.1`)

openai/gpt-4.1 is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $8.00 per 1M output tokens, with a 1.05M-token context window and up to 33K output tokens; it supports tool calling, image input, web search.

- Model ID: openai/gpt-4.1
- Type: Text
- Publisher: OpenAI
- Context window: 1,047,576 tokens
- Max output: 32,768 tokens
- Input price: $2.00 per 1M tokens
- Output price: $8.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-14
- Page: https://docs.oceantoken.ai/models/openai/gpt-4.1

### GPT-4.1 Mini (`openai/gpt-4.1-mini`)

openai/gpt-4.1-mini is a language model from OpenAI you can call on the OceanToken API at $0.40 per 1M input tokens and $1.60 per 1M output tokens, with a 1.05M-token context window and up to 33K output tokens; it supports tool calling, image input, web search.

- Model ID: openai/gpt-4.1-mini
- Type: Text
- Publisher: OpenAI
- Context window: 1,047,576 tokens
- Max output: 32,768 tokens
- Input price: $0.40 per 1M tokens
- Output price: $1.60 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Capabilities: tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-14
- Page: https://docs.oceantoken.ai/models/openai/gpt-4.1-mini

### GPT-4.1 Nano (`openai/gpt-4.1-nano`)

openai/gpt-4.1-nano is a language model from OpenAI you can call on the OceanToken API at $0.10 per 1M input tokens and $0.40 per 1M output tokens, with a 1.05M-token context window and up to 33K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4.1-nano
- Type: Text
- Publisher: OpenAI
- Context window: 1,047,576 tokens
- Max output: 32,768 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.40 per 1M tokens
- Cached input price: $0.025 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-14
- Page: https://docs.oceantoken.ai/models/openai/gpt-4.1-nano

### GPT-4o (`openai/gpt-4o`)

openai/gpt-4o is a language model from OpenAI you can call on the OceanToken API at $2.50 per 1M input tokens and $10.00 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4o
- Type: Text
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $2.50 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $1.25 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-05-13
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o

### GPT-4o 2024.05 13 (`openai/gpt-4o-2024-05-13`)

openai/gpt-4o-2024-05-13 is a language model from OpenAI you can call on the OceanToken API at $5.00 per 1M input tokens and $15.00 per 1M output tokens, with a 128K-token context window and up to 4K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4o-2024-05-13
- Type: Text
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 4,096 tokens
- Input price: $5.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-05-13
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o-2024-05-13

### GPT-4o 2024.08 06 (`openai/gpt-4o-2024-08-06`)

openai/gpt-4o-2024-08-06 is a language model from OpenAI you can call on the OceanToken API at $2.50 per 1M input tokens and $10.00 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4o-2024-08-06
- Type: Text
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $2.50 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $1.25 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-08-06
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o-2024-08-06

### GPT-4o 2024.11 20 (`openai/gpt-4o-2024-11-20`)

openai/gpt-4o-2024-11-20 is a language model from OpenAI you can call on the OceanToken API at $2.50 per 1M input tokens and $10.00 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4o-2024-11-20
- Type: Text
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $2.50 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $1.25 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-11-20
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o-2024-11-20

### GPT-4o Mini (`openai/gpt-4o-mini`)

openai/gpt-4o-mini is a language model from OpenAI you can call on the OceanToken API at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4o-mini
- Type: Text
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.60 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-07-18
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o-mini

### GPT-4o Mini 2024.07 18 (`openai/gpt-4o-mini-2024-07-18`)

openai/gpt-4o-mini-2024-07-18 is a language model from OpenAI you can call on the OceanToken API at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-4o-mini-2024-07-18
- Type: Text
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.60 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-07-18
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o-mini-2024-07-18

### GPT-4o Mini Transcribe (`openai/gpt-4o-mini-transcribe`)

openai/gpt-4o-mini-transcribe is a speech-to-text model from OpenAI you can call on the OceanToken API at $1.25 per 1M input tokens and $5.00 per 1M output tokens.

- Model ID: openai/gpt-4o-mini-transcribe
- Type: Transcription
- Publisher: OpenAI
- Input price: $1.25 per 1M tokens
- Output price: $5.00 per 1M tokens
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-01
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o-mini-transcribe

### GPT-4o Transcribe (`openai/gpt-4o-transcribe`)

openai/gpt-4o-transcribe is a speech-to-text model from OpenAI you can call on the OceanToken API at $2.50 per 1M input tokens and $10.00 per 1M output tokens.

- Model ID: openai/gpt-4o-transcribe
- Type: Transcription
- Publisher: OpenAI
- Input price: $2.50 per 1M tokens
- Output price: $10.00 per 1M tokens
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/openai/gpt-4o-transcribe

### GPT-5 (`openai/gpt-5`)

openai/gpt-5 is a language model from OpenAI you can call on the OceanToken API at $1.25 per 1M input tokens and $10.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $1.25 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.125 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-07
- Page: https://docs.oceantoken.ai/models/openai/gpt-5

### GPT-5 Image (`openai/gpt-5-image`)

openai/gpt-5-image is an image generation model from OpenAI you can call on the OceanToken API at $10.00 per 1M input tokens and $40.00 per 1M output tokens, with a 400K-token context window and up to 128K output tokens; it supports reasoning, image input.

- Model ID: openai/gpt-5-image
- Type: Image
- Publisher: OpenAI
- Context window: 400,000 tokens
- Max output: 128,000 tokens
- Input price: $10.00 per 1M tokens
- Output price: $40.00 per 1M tokens
- Cached input price: $1.25 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-14
- Page: https://docs.oceantoken.ai/models/openai/gpt-5-image

### GPT-5 Image Mini (`openai/gpt-5-image-mini`)

openai/gpt-5-image-mini is an image generation model from OpenAI you can call on the OceanToken API at $2.50 per 1M input tokens and $8.00 per 1M output tokens, with a 400K-token context window and up to 128K output tokens; it supports reasoning, image input.

- Model ID: openai/gpt-5-image-mini
- Type: Image
- Publisher: OpenAI
- Context window: 400,000 tokens
- Max output: 128,000 tokens
- Input price: $2.50 per 1M tokens
- Output price: $8.00 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-16
- Page: https://docs.oceantoken.ai/models/openai/gpt-5-image-mini

### GPT-5 Mini (`openai/gpt-5-mini`)

openai/gpt-5-mini is a language model from OpenAI you can call on the OceanToken API at $0.25 per 1M input tokens and $2.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5-mini
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $0.25 per 1M tokens
- Output price: $2.00 per 1M tokens
- Cached input price: $0.025 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-07
- Page: https://docs.oceantoken.ai/models/openai/gpt-5-mini

### GPT-5 Nano (`openai/gpt-5-nano`)

openai/gpt-5-nano is a language model from OpenAI you can call on the OceanToken API at $0.05 per 1M input tokens and $0.40 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5-nano
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $0.05 per 1M tokens
- Output price: $0.40 per 1M tokens
- Cached input price: $0.005 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-07
- Page: https://docs.oceantoken.ai/models/openai/gpt-5-nano

### GPT-5 Pro (`openai/gpt-5-pro`)

openai/gpt-5-pro is a language model from OpenAI you can call on the OceanToken API at $15.00 per 1M input tokens and $120.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5-pro
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $15.00 per 1M tokens
- Output price: $120.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-06
- Page: https://docs.oceantoken.ai/models/openai/gpt-5-pro

### GPT-5.1 (`openai/gpt-5.1`)

openai/gpt-5.1 is a language model from OpenAI you can call on the OceanToken API at $1.25 per 1M input tokens and $10.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5.1
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $1.25 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.125 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-13
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.1

### GPT-5.1 Codex (`openai/gpt-5.1-codex`)

openai/gpt-5.1-codex is a language model from OpenAI you can call on the OceanToken API at $1.25 per 1M input tokens and $10.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.1-codex
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $1.25 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.13 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-13
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.1-codex

### GPT-5.1 Codex Max (`openai/gpt-5.1-codex-max`)

openai/gpt-5.1-codex-max is a language model from OpenAI you can call on the OceanToken API at $1.25 per 1M input tokens and $10.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.1-codex-max
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $1.25 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.125 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-04
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.1-codex-max

### GPT-5.1 Codex Mini (`openai/gpt-5.1-codex-mini`)

openai/gpt-5.1-codex-mini is a language model from OpenAI you can call on the OceanToken API at $0.25 per 1M input tokens and $2.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.1-codex-mini
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $0.25 per 1M tokens
- Output price: $2.00 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-13
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.1-codex-mini

### GPT-5.2 (`openai/gpt-5.2`)

openai/gpt-5.2 is a language model from OpenAI you can call on the OceanToken API at $1.75 per 1M input tokens and $14.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5.2
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $1.75 per 1M tokens
- Output price: $14.00 per 1M tokens
- Cached input price: $0.175 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-10
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.2

### GPT-5.2 Codex (`openai/gpt-5.2-codex`)

openai/gpt-5.2-codex is a language model from OpenAI you can call on the OceanToken API at $1.75 per 1M input tokens and $14.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.2-codex
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $1.75 per 1M tokens
- Output price: $14.00 per 1M tokens
- Cached input price: $0.175 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-14
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.2-codex

### GPT-5.2 Pro (`openai/gpt-5.2-pro`)

openai/gpt-5.2-pro is a language model from OpenAI you can call on the OceanToken API at $21.00 per 1M input tokens and $168.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.2-pro
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $21.00 per 1M tokens
- Output price: $168.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-10
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.2-pro

### GPT-5.3 Codex (`openai/gpt-5.3-codex`)

openai/gpt-5.3-codex is a language model from OpenAI you can call on the OceanToken API at $1.75 per 1M input tokens and $14.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.3-codex
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $1.75 per 1M tokens
- Output price: $14.00 per 1M tokens
- Cached input price: $0.175 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-24
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.3-codex

### GPT-5.4 (`openai/gpt-5.4`)

openai/gpt-5.4 is a language model from OpenAI you can call on the OceanToken API at $2.50 per 1M input tokens and $15.00 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.4
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $2.50 per 1M tokens
- Output price: $15.00 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-05
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.4

### GPT-5.4 Image 2 (`openai/gpt-5.4-image-2`)

openai/gpt-5.4-image-2 is an image generation model from OpenAI you can call on the OceanToken API at $8.00 per 1M input tokens and $30.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, image input.

- Model ID: openai/gpt-5.4-image-2
- Type: Image
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $8.00 per 1M tokens
- Output price: $30.00 per 1M tokens
- Cached input price: $2.00 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-21
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.4-image-2

### GPT-5.4 Mini (`openai/gpt-5.4-mini`)

openai/gpt-5.4-mini is a language model from OpenAI you can call on the OceanToken API at $0.75 per 1M input tokens and $4.50 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5.4-mini
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $0.75 per 1M tokens
- Output price: $4.50 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-17
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.4-mini

### GPT-5.4 Nano (`openai/gpt-5.4-nano`)

openai/gpt-5.4-nano is a language model from OpenAI you can call on the OceanToken API at $0.20 per 1M input tokens and $1.25 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5.4-nano
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $0.20 per 1M tokens
- Output price: $1.25 per 1M tokens
- Cached input price: $0.02 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-17
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.4-nano

### GPT-5.4 Pro (`openai/gpt-5.4-pro`)

openai/gpt-5.4-pro is a language model from OpenAI you can call on the OceanToken API at $30.00 per 1M input tokens and $180.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.4-pro
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $30.00 per 1M tokens
- Output price: $180.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-05
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.4-pro

### GPT-5.5 (`openai/gpt-5.5`)

openai/gpt-5.5 is a language model from OpenAI you can call on the OceanToken API at $5.00 per 1M input tokens and $30.00 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input, web search.

- Model ID: openai/gpt-5.5
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $30.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input, web search
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-24
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.5

### GPT-5.5 Pro (`openai/gpt-5.5-pro`)

openai/gpt-5.5-pro is a language model from OpenAI you can call on the OceanToken API at $30.00 per 1M input tokens and $180.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.5-pro
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $30.00 per 1M tokens
- Output price: $180.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-24
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.5-pro

### GPT-5.6 Luna (`openai/gpt-5.6-luna`)

openai/gpt-5.6-luna is a language model from OpenAI you can call on the OceanToken API at $0.20 per 1M input tokens and $1.20 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.6-luna
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $0.20 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.02 per 1M tokens
- Cache write price: $0.25 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.6-luna

### GPT-5.6 Luna Pro (`openai/gpt-5.6-luna-pro`)

openai/gpt-5.6-luna-pro is a language model from OpenAI you can call on the OceanToken API at $0.20 per 1M input tokens and $1.20 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.6-luna-pro
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $0.20 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.02 per 1M tokens
- Cache write price: $0.25 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.6-luna-pro

### GPT-5.6 Sol (`openai/gpt-5.6-sol`)

openai/gpt-5.6-sol is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.6-sol
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.6-sol

### GPT-5.6 Sol Pro (`openai/gpt-5.6-sol-pro`)

openai/gpt-5.6-sol-pro is a language model from OpenAI you can call on the OceanToken API at $4.00 per 1M input tokens and $20.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.6-sol-pro
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $4.00 per 1M tokens
- Output price: $20.00 per 1M tokens
- Cached input price: $0.40 per 1M tokens
- Cache write price: $5.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.6-sol-pro

### GPT-5.6 Terra (`openai/gpt-5.6-terra`)

openai/gpt-5.6-terra is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $12.00 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.6-terra
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $12.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.6-terra

### GPT-5.6 Terra Pro (`openai/gpt-5.6-terra-pro`)

openai/gpt-5.6-terra-pro is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $12.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-5.6-terra-pro
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $12.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-5.6-terra-pro

### GPT-6 Astra (`openai/gpt-6-astra`)

openai/gpt-6-astra is a language model from OpenAI you can call on the OceanToken API at $10.00 per 1M input tokens and $50.00 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-6-astra
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $10.00 per 1M tokens
- Output price: $50.00 per 1M tokens
- Cached input price: $1.00 per 1M tokens
- Cache write price: $12.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-04
- Page: https://docs.oceantoken.ai/models/openai/gpt-6-astra

### GPT-6 Astra Pro (`openai/gpt-6-astra-pro`)

openai/gpt-6-astra-pro is a language model from OpenAI you can call on the OceanToken API at $10.00 per 1M input tokens and $50.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-6-astra-pro
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $10.00 per 1M tokens
- Output price: $50.00 per 1M tokens
- Cached input price: $1.00 per 1M tokens
- Cache write price: $12.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-04
- Page: https://docs.oceantoken.ai/models/openai/gpt-6-astra-pro

### GPT-6 Luna (`openai/gpt-6-luna`)

openai/gpt-6-luna is a language model from OpenAI you can call on the OceanToken API at $0.10 per 1M input tokens and $0.50 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-6-luna
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.50 per 1M tokens
- Cached input price: $0.01 per 1M tokens
- Cache write price: $0.125 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-22
- Page: https://docs.oceantoken.ai/models/openai/gpt-6-luna

### GPT-6 Sol (`openai/gpt-6-sol`)

openai/gpt-6-sol is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-6-sol
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-22
- Page: https://docs.oceantoken.ai/models/openai/gpt-6-sol

### GPT-6.1 Sol (`openai/gpt-6.1-sol`)

openai/gpt-6.1-sol is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 1.05M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-6.1-sol
- Type: Text
- Publisher: OpenAI
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-29
- Page: https://docs.oceantoken.ai/models/openai/gpt-6.1-sol

### GPT Astra Latest (`openai/gpt-astra-latest`)

openai/gpt-astra-latest is a language model from OpenAI you can call on the OceanToken API at $10.00 per 1M input tokens and $50.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-astra-latest
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $10.00 per 1M tokens
- Output price: $50.00 per 1M tokens
- Cached input price: $1.00 per 1M tokens
- Cache write price: $12.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: openai/gpt-6-astra
- In the catalog since: 2026-09-11
- Page: https://docs.oceantoken.ai/models/openai/gpt-astra-latest

### GPT Audio (`openai/gpt-audio`)

openai/gpt-audio is a language model from OpenAI you can call on the OceanToken API at $2.50 per 1M input tokens and $10.00 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports tool calling, audio output.

- Model ID: openai/gpt-audio
- Type: Audio
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $2.50 per 1M tokens
- Output price: $10.00 per 1M tokens
- Capabilities: tool calling, audio output
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-19
- Page: https://docs.oceantoken.ai/models/openai/gpt-audio

### GPT Audio Mini (`openai/gpt-audio-mini`)

openai/gpt-audio-mini is a language model from OpenAI you can call on the OceanToken API at $0.60 per 1M input tokens and $2.40 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports tool calling, audio output.

- Model ID: openai/gpt-audio-mini
- Type: Audio
- Publisher: OpenAI
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $0.60 per 1M tokens
- Output price: $2.40 per 1M tokens
- Capabilities: tool calling, audio output
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-19
- Page: https://docs.oceantoken.ai/models/openai/gpt-audio-mini

### GPT Chat Latest (`openai/gpt-chat-latest`)

openai/gpt-chat-latest is a language model from OpenAI you can call on the OceanToken API at $5.00 per 1M input tokens and $30.00 per 1M output tokens, with a 272K-token context window and up to 128K output tokens; it supports tool calling, image input.

- Model ID: openai/gpt-chat-latest
- Type: Text
- Publisher: OpenAI
- Context window: 272,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $30.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-05
- Page: https://docs.oceantoken.ai/models/openai/gpt-chat-latest

### GPT Image 1 (`openai/gpt-image-1`)

openai/gpt-image-1 is an image generation model from OpenAI you can call on the OceanToken API at $5.00 per 1M input tokens and $40.00 per 1M output image tokens.

- Model ID: openai/gpt-image-1
- Type: Image
- Publisher: OpenAI
- Input price: $5.00 per 1M tokens
- Output price: $40.00 per 1M image tokens
- Cached input price: $1.25 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-24
- Page: https://docs.oceantoken.ai/models/openai/gpt-image-1

### GPT Image 1 Mini (`openai/gpt-image-1-mini`)

openai/gpt-image-1-mini is an image generation model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $8.00 per 1M output image tokens.

- Model ID: openai/gpt-image-1-mini
- Type: Image
- Publisher: OpenAI
- Input price: $2.00 per 1M tokens
- Output price: $8.00 per 1M image tokens
- Cached input price: $0.20 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-24
- Page: https://docs.oceantoken.ai/models/openai/gpt-image-1-mini

### GPT Image 2 (`openai/gpt-image-2`)

openai/gpt-image-2 is an image generation model from OpenAI you can call on the OceanToken API at $5.00 per 1M input tokens and $30.00 per 1M output image tokens; it supports image input.

- Model ID: openai/gpt-image-2
- Type: Image
- Publisher: OpenAI
- Input price: $5.00 per 1M tokens
- Output price: $30.00 per 1M image tokens
- Cached input price: $1.25 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-24
- Page: https://docs.oceantoken.ai/models/openai/gpt-image-2

### GPT Image 2.5 Flare (`openai/gpt-image-2.5-flare`)

openai/gpt-image-2.5-flare is an image generation model from OpenAI you can call on the OceanToken API at $5.00 per 1M input tokens and $30.00 per 1M output image tokens; it supports image input.

- Model ID: openai/gpt-image-2.5-flare
- Type: Image
- Publisher: OpenAI
- Input price: $5.00 per 1M tokens
- Output price: $30.00 per 1M image tokens
- Cached input price: $1.25 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-image-2.5-flare

### GPT Image 2.5 Sunburst (`openai/gpt-image-2.5-sunburst`)

openai/gpt-image-2.5-sunburst is an image generation model from OpenAI you can call on the OceanToken API at $5.00 per 1M input tokens and $30.00 per 1M output image tokens; it supports image input.

- Model ID: openai/gpt-image-2.5-sunburst
- Type: Image
- Publisher: OpenAI
- Input price: $5.00 per 1M tokens
- Output price: $30.00 per 1M image tokens
- Cached input price: $1.25 per 1M tokens
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-09
- Page: https://docs.oceantoken.ai/models/openai/gpt-image-2.5-sunburst

### GPT Luna Latest (`openai/gpt-luna-latest`)

openai/gpt-luna-latest is a language model from OpenAI you can call on the OceanToken API at $0.10 per 1M input tokens and $0.50 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-luna-latest
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.50 per 1M tokens
- Cached input price: $0.01 per 1M tokens
- Cache write price: $0.125 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: openai/gpt-6-luna
- In the catalog since: 2026-09-11
- Page: https://docs.oceantoken.ai/models/openai/gpt-luna-latest

### GPT Mini Latest (`openai/gpt-mini-latest`)

openai/gpt-mini-latest is a language model from OpenAI you can call on the OceanToken API at $0.75 per 1M input tokens and $4.50 per 1M output tokens, with a 400K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-mini-latest
- Type: Text
- Publisher: OpenAI
- Context window: 400,000 tokens
- Max output: 128,000 tokens
- Input price: $0.75 per 1M tokens
- Output price: $4.50 per 1M tokens
- Cached input price: $0.075 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: openai/gpt-5.4-mini
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/openai/gpt-mini-latest

### GPT Oss 120B (`openai/gpt-oss-120b`)

openai/gpt-oss-120b is a language model from OpenAI you can call on the OceanToken API at $0.14 per 1M input tokens and $0.95 per 1M output tokens, with a 131K-token context window and up to 66K output tokens; it supports reasoning, tool calling.

- Model ID: openai/gpt-oss-120b
- Type: Text
- Publisher: OpenAI
- Context window: 131,072 tokens
- Max output: 65,536 tokens
- Input price: $0.14 per 1M tokens
- Output price: $0.95 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-05
- Page: https://docs.oceantoken.ai/models/openai/gpt-oss-120b

### GPT Oss 20B (`openai/gpt-oss-20b`)

openai/gpt-oss-20b is a language model from OpenAI you can call on the OceanToken API at $0.04 per 1M input tokens and $0.18 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: openai/gpt-oss-20b
- Type: Text
- Publisher: OpenAI
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $0.04 per 1M tokens
- Output price: $0.18 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-05
- Page: https://docs.oceantoken.ai/models/openai/gpt-oss-20b

### GPT Oss Safeguard 20B (`openai/gpt-oss-safeguard-20b`)

openai/gpt-oss-safeguard-20b is a language model from OpenAI you can call on the OceanToken API at $0.075 per 1M input tokens and $0.30 per 1M output tokens, with a 131K-token context window and up to 66K output tokens; it supports reasoning, tool calling.

- Model ID: openai/gpt-oss-safeguard-20b
- Type: Text
- Publisher: OpenAI
- Context window: 131,072 tokens
- Max output: 65,536 tokens
- Input price: $0.075 per 1M tokens
- Output price: $0.30 per 1M tokens
- Cached input price: $0.0375 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-29
- Page: https://docs.oceantoken.ai/models/openai/gpt-oss-safeguard-20b

### GPT Sol Latest (`openai/gpt-sol-latest`)

openai/gpt-sol-latest is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-sol-latest
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $10.00 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: openai/gpt-6.1-sol
- In the catalog since: 2026-09-11
- Page: https://docs.oceantoken.ai/models/openai/gpt-sol-latest

### GPT Terra Latest (`openai/gpt-terra-latest`)

openai/gpt-terra-latest is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $12.00 per 1M output tokens, with a 922K-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/gpt-terra-latest
- Type: Text
- Publisher: OpenAI
- Context window: 922,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $12.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: openai/gpt-5.6-terra
- In the catalog since: 2026-09-11
- Page: https://docs.oceantoken.ai/models/openai/gpt-terra-latest

### GPT Transcribe (`openai/gpt-transcribe`)

openai/gpt-transcribe is a speech-to-text model from OpenAI you can call on the OceanToken API at $0.0045 per minute of audio.

- Model ID: openai/gpt-transcribe
- Type: Transcription
- Publisher: OpenAI
- Price: $0.0045 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-05
- Page: https://docs.oceantoken.ai/models/openai/gpt-transcribe

### o1 (`openai/o1`)

openai/o1 is a language model from OpenAI you can call on the OceanToken API at $15.00 per 1M input tokens and $60.00 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/o1
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $15.00 per 1M tokens
- Output price: $60.00 per 1M tokens
- Cached input price: $7.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-17
- Page: https://docs.oceantoken.ai/models/openai/o1

### o1-pro (`openai/o1-pro`)

openai/o1-pro is a language model from OpenAI you can call on the OceanToken API at $150.00 per 1M input tokens and $600.00 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, image input.

- Model ID: openai/o1-pro
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $150.00 per 1M tokens
- Output price: $600.00 per 1M tokens
- Capabilities: reasoning, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-19
- Page: https://docs.oceantoken.ai/models/openai/o1-pro

### o3 (`openai/o3`)

openai/o3 is a language model from OpenAI you can call on the OceanToken API at $2.00 per 1M input tokens and $8.00 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/o3
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $8.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-16
- Page: https://docs.oceantoken.ai/models/openai/o3

### o3-mini (`openai/o3-mini`)

openai/o3-mini is a language model from OpenAI you can call on the OceanToken API at $1.10 per 1M input tokens and $4.40 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, tool calling.

- Model ID: openai/o3-mini
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $1.10 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.55 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-01-31
- Page: https://docs.oceantoken.ai/models/openai/o3-mini

### o3-mini High (`openai/o3-mini-high`)

openai/o3-mini-high is a language model from OpenAI you can call on the OceanToken API at $1.10 per 1M input tokens and $4.40 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, tool calling.

- Model ID: openai/o3-mini-high
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $1.10 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.55 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-02-12
- Page: https://docs.oceantoken.ai/models/openai/o3-mini-high

### o3-pro (`openai/o3-pro`)

openai/o3-pro is a language model from OpenAI you can call on the OceanToken API at $20.00 per 1M input tokens and $80.00 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/o3-pro
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $20.00 per 1M tokens
- Output price: $80.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-06-10
- Page: https://docs.oceantoken.ai/models/openai/o3-pro

### o4-mini (`openai/o4-mini`)

openai/o4-mini is a language model from OpenAI you can call on the OceanToken API at $1.10 per 1M input tokens and $4.40 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/o4-mini
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $1.10 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.275 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-16
- Page: https://docs.oceantoken.ai/models/openai/o4-mini

### o4-mini High (`openai/o4-mini-high`)

openai/o4-mini-high is a language model from OpenAI you can call on the OceanToken API at $1.10 per 1M input tokens and $4.40 per 1M output tokens, with a 200K-token context window and up to 100K output tokens; it supports reasoning, tool calling, image input.

- Model ID: openai/o4-mini-high
- Type: Text
- Publisher: OpenAI
- Context window: 200,000 tokens
- Max output: 100,000 tokens
- Input price: $1.10 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.275 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-16
- Page: https://docs.oceantoken.ai/models/openai/o4-mini-high

### Sora 2 Pro (`openai/sora-2-pro`)

openai/sora-2-pro is a video generation model from OpenAI you can call on the OceanToken API at from $0.30 per second of generated video.

- Model ID: openai/sora-2-pro
- Type: Video
- Publisher: OpenAI
- Price: from $0.30 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- Page: https://docs.oceantoken.ai/models/openai/sora-2-pro

### Text Embedding 3 Large (`openai/text-embedding-3-large`)

openai/text-embedding-3-large is a text embedding model from OpenAI you can call on the OceanToken API at $0.13 per 1M input tokens, with a 8K-token context window.

- Model ID: openai/text-embedding-3-large
- Type: Embeddings
- Publisher: OpenAI
- Context window: 8,191 tokens
- Input price: $0.13 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-30
- Page: https://docs.oceantoken.ai/models/openai/text-embedding-3-large

### Text Embedding 3 Small (`openai/text-embedding-3-small`)

openai/text-embedding-3-small is a text embedding model from OpenAI you can call on the OceanToken API at $0.02 per 1M input tokens, with a 8K-token context window.

- Model ID: openai/text-embedding-3-small
- Type: Embeddings
- Publisher: OpenAI
- Context window: 8,191 tokens
- Input price: $0.02 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-30
- Page: https://docs.oceantoken.ai/models/openai/text-embedding-3-small

### Text Embedding Ada 002 (`openai/text-embedding-ada-002`)

openai/text-embedding-ada-002 is a text embedding model from OpenAI you can call on the OceanToken API at $0.10 per 1M input tokens, with a 8K-token context window.

- Model ID: openai/text-embedding-ada-002
- Type: Embeddings
- Publisher: OpenAI
- Context window: 8,191 tokens
- Input price: $0.10 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-30
- Page: https://docs.oceantoken.ai/models/openai/text-embedding-ada-002

### Whisper 1 (`openai/whisper-1`)

openai/whisper-1 is a speech-to-text model from OpenAI you can call on the OceanToken API at $0.006 per minute of audio.

- Model ID: openai/whisper-1
- Type: Transcription
- Publisher: OpenAI
- Price: $0.006 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/openai/whisper-1

### Whisper Large V3 (`openai/whisper-large-v3`)

openai/whisper-large-v3 is a speech-to-text model from OpenAI you can call on the OceanToken API at $0.00045 per minute of audio.

- Model ID: openai/whisper-large-v3
- Type: Transcription
- Publisher: OpenAI
- Price: $0.00045 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-01
- Page: https://docs.oceantoken.ai/models/openai/whisper-large-v3

### Whisper Large V3 Turbo (`openai/whisper-large-v3-turbo`)

openai/whisper-large-v3-turbo is a speech-to-text model from OpenAI you can call on the OceanToken API at $0.0002 per minute of audio.

- Model ID: openai/whisper-large-v3-turbo
- Type: Transcription
- Publisher: OpenAI
- Price: $0.0002 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-01
- Page: https://docs.oceantoken.ai/models/openai/whisper-large-v3-turbo

## Perceptron models

Index: https://docs.oceantoken.ai/models/perceptron

### Perceptron Mk1 (`perceptron/perceptron-mk1`)

perceptron/perceptron-mk1 is a language model from Perceptron you can call on the OceanToken API at $0.15 per 1M input tokens and $1.50 per 1M output tokens, with a 33K-token context window and up to 8K output tokens; it supports reasoning, image input.

- Model ID: perceptron/perceptron-mk1
- Type: Text
- Publisher: Perceptron
- Context window: 32,768 tokens
- Max output: 8,192 tokens
- Input price: $0.15 per 1M tokens
- Output price: $1.50 per 1M tokens
- Capabilities: reasoning, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-12
- Page: https://docs.oceantoken.ai/models/perceptron/perceptron-mk1

## Perplexity models

Index: https://docs.oceantoken.ai/models/perplexity

### Pplx Embed V1 0.6b (`perplexity/pplx-embed-v1-0.6b`)

perplexity/pplx-embed-v1-0.6b is a text embedding model from Perplexity you can call on the OceanToken API at $0.004 per 1M input tokens, with a 32K-token context window.

- Model ID: perplexity/pplx-embed-v1-0.6b
- Type: Embeddings
- Publisher: Perplexity
- Context window: 32,000 tokens
- Input price: $0.004 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-16
- Page: https://docs.oceantoken.ai/models/perplexity/pplx-embed-v1-0.6b

### Pplx Embed V1 4B (`perplexity/pplx-embed-v1-4b`)

perplexity/pplx-embed-v1-4b is a text embedding model from Perplexity you can call on the OceanToken API at $0.03 per 1M input tokens, with a 32K-token context window.

- Model ID: perplexity/pplx-embed-v1-4b
- Type: Embeddings
- Publisher: Perplexity
- Context window: 32,000 tokens
- Input price: $0.03 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-16
- Page: https://docs.oceantoken.ai/models/perplexity/pplx-embed-v1-4b

### Sonar (`perplexity/sonar`)

perplexity/sonar is a language model from Perplexity you can call on the OceanToken API at $1.00 per 1M input tokens and $1.00 per 1M output tokens, with a 127K-token context window and up to 114K output tokens; it supports image input.

- Model ID: perplexity/sonar
- Type: Text
- Publisher: Perplexity
- Context window: 127,072 tokens
- Max output: 114,364 tokens
- Input price: $1.00 per 1M tokens
- Output price: $1.00 per 1M tokens
- Capabilities: image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-01-27
- Page: https://docs.oceantoken.ai/models/perplexity/sonar

### Sonar Deep Research (`perplexity/sonar-deep-research`)

perplexity/sonar-deep-research is a language model from Perplexity you can call on the OceanToken API at $2.00 per 1M input tokens and $8.00 per 1M output tokens, with a 128K-token context window and up to 115K output tokens; it supports reasoning.

- Model ID: perplexity/sonar-deep-research
- Type: Text
- Publisher: Perplexity
- Context window: 128,000 tokens
- Max output: 115,200 tokens
- Input price: $2.00 per 1M tokens
- Output price: $8.00 per 1M tokens
- Capabilities: reasoning
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-07
- Page: https://docs.oceantoken.ai/models/perplexity/sonar-deep-research

### Sonar Pro (`perplexity/sonar-pro`)

perplexity/sonar-pro is a language model from Perplexity you can call on the OceanToken API at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a 200K-token context window and up to 8K output tokens; it supports image input.

- Model ID: perplexity/sonar-pro
- Type: Text
- Publisher: Perplexity
- Context window: 200,000 tokens
- Max output: 8,000 tokens
- Input price: $3.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Capabilities: image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-07
- Page: https://docs.oceantoken.ai/models/perplexity/sonar-pro

### Sonar Pro Search (`perplexity/sonar-pro-search`)

perplexity/sonar-pro-search is a language model from Perplexity you can call on the OceanToken API at $3.00 per 1M input tokens and $15.00 per 1M output tokens, with a 200K-token context window and up to 8K output tokens; it supports reasoning, image input.

- Model ID: perplexity/sonar-pro-search
- Type: Text
- Publisher: Perplexity
- Context window: 200,000 tokens
- Max output: 8,000 tokens
- Input price: $3.00 per 1M tokens
- Output price: $15.00 per 1M tokens
- Capabilities: reasoning, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-30
- Page: https://docs.oceantoken.ai/models/perplexity/sonar-pro-search

### Sonar Reasoning Pro (`perplexity/sonar-reasoning-pro`)

perplexity/sonar-reasoning-pro is a language model from Perplexity you can call on the OceanToken API at $2.00 per 1M input tokens and $8.00 per 1M output tokens, with a 128K-token context window and up to 115K output tokens; it supports reasoning, image input.

- Model ID: perplexity/sonar-reasoning-pro
- Type: Text
- Publisher: Perplexity
- Context window: 128,000 tokens
- Max output: 115,200 tokens
- Input price: $2.00 per 1M tokens
- Output price: $8.00 per 1M tokens
- Capabilities: reasoning, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-07
- Page: https://docs.oceantoken.ai/models/perplexity/sonar-reasoning-pro

## Poolside models

Index: https://docs.oceantoken.ai/models/poolside

### Laguna S 2.1 (`poolside/laguna-s-2.1`)

poolside/laguna-s-2.1 is a language model from Poolside you can call on the OceanToken API at $0.09 per 1M input tokens and $0.18 per 1M output tokens, with a 1.05M-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: poolside/laguna-s-2.1
- Type: Text
- Publisher: Poolside
- Context window: 1,048,576 tokens
- Max output: 131,072 tokens
- Input price: $0.09 per 1M tokens
- Output price: $0.18 per 1M tokens
- Cached input price: $0.009 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-21
- Scheduled retirement: 2026-10-31
- Page: https://docs.oceantoken.ai/models/poolside/laguna-s-2.1

### Laguna S 2.1 (Free) (`poolside/laguna-s-2.1:free`)

poolside/laguna-s-2.1:free is a language model from Poolside you can call free of charge on the OceanToken API, rate-limited, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: poolside/laguna-s-2.1:free
- Type: Text
- Publisher: Poolside
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-21
- Scheduled retirement: 2026-10-31
- Page: https://docs.oceantoken.ai/models/poolside/laguna-s-2.1--free

### Laguna Xs 2.1 (`poolside/laguna-xs-2.1`)

poolside/laguna-xs-2.1 is a language model from Poolside you can call on the OceanToken API at $0.06 per 1M input tokens and $0.12 per 1M output tokens, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: poolside/laguna-xs-2.1
- Type: Text
- Publisher: Poolside
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Input price: $0.06 per 1M tokens
- Output price: $0.12 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-02
- Scheduled retirement: 2026-10-31
- Page: https://docs.oceantoken.ai/models/poolside/laguna-xs-2.1

### Laguna Xs 2.1 (Free) (`poolside/laguna-xs-2.1:free`)

poolside/laguna-xs-2.1:free is a language model from Poolside you can call free of charge on the OceanToken API, rate-limited, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling.

- Model ID: poolside/laguna-xs-2.1:free
- Type: Text
- Publisher: Poolside
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Price: Free, rate-limited
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-02
- Scheduled retirement: 2026-10-31
- Page: https://docs.oceantoken.ai/models/poolside/laguna-xs-2.1--free

## Qwen models

Index: https://docs.oceantoken.ai/models/qwen

### Qwen 2.5 72B Instruct (`qwen/qwen-2.5-72b-instruct`)

qwen/qwen-2.5-72b-instruct is a language model from Qwen you can call on the OceanToken API at $0.36 per 1M input tokens and $0.40 per 1M output tokens, with a 33K-token context window and up to 16K output tokens; it supports tool calling.

- Model ID: qwen/qwen-2.5-72b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 32,768 tokens
- Max output: 16,384 tokens
- Input price: $0.36 per 1M tokens
- Output price: $0.40 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-09-19
- Page: https://docs.oceantoken.ai/models/qwen/qwen-2.5-72b-instruct

### Qwen 2.5 7B Instruct (`qwen/qwen-2.5-7b-instruct`)

qwen/qwen-2.5-7b-instruct is a language model from Qwen you can call on the OceanToken API at $0.10 per 1M input tokens and $0.20 per 1M output tokens, with a 33K-token context window and up to 29K output tokens; it supports tool calling.

- Model ID: qwen/qwen-2.5-7b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 32,768 tokens
- Max output: 29,491 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.20 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-10-16
- Page: https://docs.oceantoken.ai/models/qwen/qwen-2.5-7b-instruct

### Qwen 2.5 Coder 32B Instruct (`qwen/qwen-2.5-coder-32b-instruct`)

qwen/qwen-2.5-coder-32b-instruct is a language model from Qwen you can call on the OceanToken API at $0.66 per 1M input tokens and $1.00 per 1M output tokens, with a 33K-token context window and up to 29K output tokens.

- Model ID: qwen/qwen-2.5-coder-32b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 32,768 tokens
- Max output: 29,491 tokens
- Input price: $0.66 per 1M tokens
- Output price: $1.00 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-11-11
- Page: https://docs.oceantoken.ai/models/qwen/qwen-2.5-coder-32b-instruct

### Qwen Audio 3.0 TTS Flash (`qwen/qwen-audio-3.0-tts-flash`)

qwen/qwen-audio-3.0-tts-flash is a text-to-speech model from Qwen you can call on the OceanToken API at $0.015 per 1,000 characters.

- Model ID: qwen/qwen-audio-3.0-tts-flash
- Type: Speech
- Publisher: Qwen
- Price: $0.015 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-23
- Page: https://docs.oceantoken.ai/models/qwen/qwen-audio-3.0-tts-flash

### Qwen Audio 3.0 TTS Plus (`qwen/qwen-audio-3.0-tts-plus`)

qwen/qwen-audio-3.0-tts-plus is a text-to-speech model from Qwen you can call on the OceanToken API at $0.02 per 1,000 characters.

- Model ID: qwen/qwen-audio-3.0-tts-plus
- Type: Speech
- Publisher: Qwen
- Price: $0.02 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-23
- Page: https://docs.oceantoken.ai/models/qwen/qwen-audio-3.0-tts-plus

### Qwen Image 3 (`qwen/qwen-image-3`)

qwen/qwen-image-3 is an image generation model from Qwen you can call on the OceanToken API at $0.03 per generated image; it supports image input.

- Model ID: qwen/qwen-image-3
- Type: Image
- Publisher: Qwen
- Price: $0.03 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-05
- Page: https://docs.oceantoken.ai/models/qwen/qwen-image-3

### Qwen Image 3 Pro (`qwen/qwen-image-3-pro`)

qwen/qwen-image-3-pro is an image generation model from Qwen you can call on the OceanToken API at $0.075 per generated image; it supports image input.

- Model ID: qwen/qwen-image-3-pro
- Type: Image
- Publisher: Qwen
- Price: $0.075 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-05
- Page: https://docs.oceantoken.ai/models/qwen/qwen-image-3-pro

### Qwen Plus (`qwen/qwen-plus`)

qwen/qwen-plus is a language model from Qwen you can call on the OceanToken API at $0.26 per 1M input tokens and $0.78 per 1M output tokens, with a 996K-token context window and up to 33K output tokens; it supports tool calling.

- Model ID: qwen/qwen-plus
- Type: Text
- Publisher: Qwen
- Context window: 995,904 tokens
- Max output: 32,768 tokens
- Input price: $0.26 per 1M tokens
- Output price: $0.78 per 1M tokens
- Cached input price: $0.052 per 1M tokens
- Cache write price: $0.325 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-02-01
- Page: https://docs.oceantoken.ai/models/qwen/qwen-plus

### Qwen2.5 VL 72B Instruct (`qwen/qwen2.5-vl-72b-instruct`)

qwen/qwen2.5-vl-72b-instruct is a language model from Qwen you can call on the OceanToken API at $0.80 per 1M input tokens and $1.00 per 1M output tokens, with a 128K-token context window and up to 115K output tokens; it supports image input.

- Model ID: qwen/qwen2.5-vl-72b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 128,000 tokens
- Max output: 115,200 tokens
- Input price: $0.80 per 1M tokens
- Output price: $1.00 per 1M tokens
- Cached input price: $0.40 per 1M tokens
- Capabilities: image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-02-01
- Page: https://docs.oceantoken.ai/models/qwen/qwen2.5-vl-72b-instruct

### Qwen3 14B (`qwen/qwen3-14b`)

qwen/qwen3-14b is a language model from Qwen you can call on the OceanToken API at $0.12 per 1M input tokens and $0.24 per 1M output tokens, with a 41K-token context window and up to 16K output tokens; it supports reasoning, tool calling.

- Model ID: qwen/qwen3-14b
- Type: Text
- Publisher: Qwen
- Context window: 40,960 tokens
- Max output: 16,384 tokens
- Input price: $0.12 per 1M tokens
- Output price: $0.24 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-28
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-14b

### Qwen3 235B A22B 2507 (`qwen/qwen3-235b-a22b-2507`)

qwen/qwen3-235b-a22b-2507 is a language model from Qwen you can call on the OceanToken API at $0.15 per 1M input tokens and $0.75 per 1M output tokens, with a 262K-token context window and up to 16K output tokens; it supports tool calling.

- Model ID: qwen/qwen3-235b-a22b-2507
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 16,384 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.75 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-21
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-235b-a22b-2507

### Qwen3 235B A22B Thinking 2507 (`qwen/qwen3-235b-a22b-thinking-2507`)

qwen/qwen3-235b-a22b-thinking-2507 is a language model from Qwen you can call on the OceanToken API at $0.45 per 1M input tokens and $3.50 per 1M output tokens, with a 128K-token context window and up to 16K output tokens; it supports reasoning, tool calling.

- Model ID: qwen/qwen3-235b-a22b-thinking-2507
- Type: Text
- Publisher: Qwen
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Input price: $0.45 per 1M tokens
- Output price: $3.50 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-25
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-235b-a22b-thinking-2507

### Qwen3 30B A3B (`qwen/qwen3-30b-a3b`)

qwen/qwen3-30b-a3b is a language model from Qwen you can call on the OceanToken API at $0.12 per 1M input tokens and $0.50 per 1M output tokens, with a 41K-token context window and up to 16K output tokens; it supports reasoning, tool calling.

- Model ID: qwen/qwen3-30b-a3b
- Type: Text
- Publisher: Qwen
- Context window: 40,960 tokens
- Max output: 16,384 tokens
- Input price: $0.12 per 1M tokens
- Output price: $0.50 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-28
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-30b-a3b

### Qwen3 30B A3B Instruct 2507 (`qwen/qwen3-30b-a3b-instruct-2507`)

qwen/qwen3-30b-a3b-instruct-2507 is a language model from Qwen you can call on the OceanToken API at $0.09 per 1M input tokens and $0.30 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports tool calling.

- Model ID: qwen/qwen3-30b-a3b-instruct-2507
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.09 per 1M tokens
- Output price: $0.30 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-29
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-30b-a3b-instruct-2507

### Qwen3 32B (`qwen/qwen3-32b`)

qwen/qwen3-32b is a language model from Qwen you can call on the OceanToken API at $0.14 per 1M input tokens and $0.40 per 1M output tokens, with a 131K-token context window and up to 16K output tokens; it supports reasoning, tool calling.

- Model ID: qwen/qwen3-32b
- Type: Text
- Publisher: Qwen
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.14 per 1M tokens
- Output price: $0.40 per 1M tokens
- Cached input price: $0.09 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-04-28
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-32b

### Qwen3 ASR 0.6b (`qwen/qwen3-asr-0.6b`)

qwen/qwen3-asr-0.6b is a speech-to-text model from Qwen you can call on the OceanToken API at $0.0002 per minute of audio.

- Model ID: qwen/qwen3-asr-0.6b
- Type: Transcription
- Publisher: Qwen
- Price: $0.0002 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-asr-0.6b

### Qwen3 ASR 1.7b (`qwen/qwen3-asr-1.7b`)

qwen/qwen3-asr-1.7b is a speech-to-text model from Qwen you can call on the OceanToken API at $0.00045 per minute of audio.

- Model ID: qwen/qwen3-asr-1.7b
- Type: Transcription
- Publisher: Qwen
- Price: $0.00045 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-asr-1.7b

### Qwen3 Coder (`qwen/qwen3-coder`)

qwen/qwen3-coder is a language model from Qwen you can call on the OceanToken API at $0.30 per 1M input tokens and $1.00 per 1M output tokens, with a 262K-token context window and up to 66K output tokens; it supports tool calling.

- Model ID: qwen/qwen3-coder
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 65,536 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.00 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-23
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-coder

### Qwen3 Coder 30B A3B Instruct (`qwen/qwen3-coder-30b-a3b-instruct`)

qwen/qwen3-coder-30b-a3b-instruct is a language model from Qwen you can call on the OceanToken API at $0.07 per 1M input tokens and $0.28 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports tool calling.

- Model ID: qwen/qwen3-coder-30b-a3b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.07 per 1M tokens
- Output price: $0.28 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-31
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-coder-30b-a3b-instruct

### Qwen3 Coder Flash (`qwen/qwen3-coder-flash`)

qwen/qwen3-coder-flash is a language model from Qwen you can call on the OceanToken API at $0.195 per 1M input tokens and $0.975 per 1M output tokens, with a 998K-token context window and up to 66K output tokens; it supports tool calling.

- Model ID: qwen/qwen3-coder-flash
- Type: Text
- Publisher: Qwen
- Context window: 997,952 tokens
- Max output: 65,536 tokens
- Input price: $0.195 per 1M tokens
- Output price: $0.975 per 1M tokens
- Cached input price: $0.039 per 1M tokens
- Cache write price: $0.244 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-17
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-coder-flash

### Qwen3 Coder Next (`qwen/qwen3-coder-next`)

qwen/qwen3-coder-next is a language model from Qwen you can call on the OceanToken API at $0.12 per 1M input tokens and $0.80 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports tool calling.

- Model ID: qwen/qwen3-coder-next
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.12 per 1M tokens
- Output price: $0.80 per 1M tokens
- Cached input price: $0.07 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-04
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-coder-next

### Qwen3 Embedding 4B (`qwen/qwen3-embedding-4b`)

qwen/qwen3-embedding-4b is a text embedding model from Qwen you can call on the OceanToken API at $0.02 per 1M input tokens, with a 33K-token context window.

- Model ID: qwen/qwen3-embedding-4b
- Type: Embeddings
- Publisher: Qwen
- Context window: 32,768 tokens
- Input price: $0.02 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-28
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-embedding-4b

### Qwen3 Embedding 8B (`qwen/qwen3-embedding-8b`)

qwen/qwen3-embedding-8b is a text embedding model from Qwen you can call on the OceanToken API at $0.01 per 1M input tokens, with a 41K-token context window and up to 32K output tokens.

- Model ID: qwen/qwen3-embedding-8b
- Type: Embeddings
- Publisher: Qwen
- Context window: 40,960 tokens
- Max output: 32,000 tokens
- Input price: $0.01 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-28
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-embedding-8b

### Qwen3 Next 80B A3B Instruct (`qwen/qwen3-next-80b-a3b-instruct`)

qwen/qwen3-next-80b-a3b-instruct is a language model from Qwen you can call on the OceanToken API at $0.10 per 1M input tokens and $1.10 per 1M output tokens, with a 262K-token context window and up to 16K output tokens; it supports tool calling.

- Model ID: qwen/qwen3-next-80b-a3b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 16,384 tokens
- Input price: $0.10 per 1M tokens
- Output price: $1.10 per 1M tokens
- Cached input price: $0.07 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-11
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-next-80b-a3b-instruct

### Qwen3 Next 80B A3B Thinking (`qwen/qwen3-next-80b-a3b-thinking`)

qwen/qwen3-next-80b-a3b-thinking is a language model from Qwen you can call on the OceanToken API at $0.15 per 1M input tokens and $1.20 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling.

- Model ID: qwen/qwen3-next-80b-a3b-thinking
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.15 per 1M tokens
- Output price: $1.20 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-11
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-next-80b-a3b-thinking

### Qwen3 Reranker 8B (`qwen/qwen3-reranker-8b`)

qwen/qwen3-reranker-8b is a reranking model from Qwen you can call on the OceanToken API at $0.20 per 1M input tokens.

- Model ID: qwen/qwen3-reranker-8b
- Type: Rerank
- Publisher: Qwen
- Input price: $0.20 per 1M tokens
- Endpoint: /v1/rerank
- API shape: Cohere rerank
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-reranker-8b

### Qwen3 VL 235B A22B Instruct (`qwen/qwen3-vl-235b-a22b-instruct`)

qwen/qwen3-vl-235b-a22b-instruct is a language model from Qwen you can call on the OceanToken API at $0.21 per 1M input tokens and $1.90 per 1M output tokens, with a 262K-token context window and up to 33K output tokens; it supports tool calling, image input.

- Model ID: qwen/qwen3-vl-235b-a22b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Input price: $0.21 per 1M tokens
- Output price: $1.90 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-23
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-vl-235b-a22b-instruct

### Qwen3 VL 30B A3B Instruct (`qwen/qwen3-vl-30b-a3b-instruct`)

qwen/qwen3-vl-30b-a3b-instruct is a language model from Qwen you can call on the OceanToken API at $0.20 per 1M input tokens and $0.70 per 1M output tokens, with a 262K-token context window and up to 16K output tokens; it supports tool calling, image input.

- Model ID: qwen/qwen3-vl-30b-a3b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 16,384 tokens
- Input price: $0.20 per 1M tokens
- Output price: $0.70 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-06
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-vl-30b-a3b-instruct

### Qwen3 VL 30B A3B Thinking (`qwen/qwen3-vl-30b-a3b-thinking`)

qwen/qwen3-vl-30b-a3b-thinking is a language model from Qwen you can call on the OceanToken API at $0.29 per 1M input tokens and $1.00 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3-vl-30b-a3b-thinking
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.29 per 1M tokens
- Output price: $1.00 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-06
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-vl-30b-a3b-thinking

### Qwen3 VL 8B Instruct (`qwen/qwen3-vl-8b-instruct`)

qwen/qwen3-vl-8b-instruct is a language model from Qwen you can call on the OceanToken API at $0.25 per 1M input tokens and $0.75 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports tool calling, image input.

- Model ID: qwen/qwen3-vl-8b-instruct
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.25 per 1M tokens
- Output price: $0.75 per 1M tokens
- Cached input price: $0.12 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-10-14
- Page: https://docs.oceantoken.ai/models/qwen/qwen3-vl-8b-instruct

### Qwen3.5 122B A10B (`qwen/qwen3.5-122b-a10b`)

qwen/qwen3.5-122b-a10b is a language model from Qwen you can call on the OceanToken API at $0.26 per 1M input tokens and $2.08 per 1M output tokens, with a 258K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-122b-a10b
- Type: Text
- Publisher: Qwen
- Context window: 258,048 tokens
- Max output: 65,536 tokens
- Input price: $0.26 per 1M tokens
- Output price: $2.08 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-25
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-122b-a10b

### Qwen3.5 27B (`qwen/qwen3.5-27b`)

qwen/qwen3.5-27b is a language model from Qwen you can call on the OceanToken API at $0.195 per 1M input tokens and $1.56 per 1M output tokens, with a 258K-token context window and up to 82K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-27b
- Type: Text
- Publisher: Qwen
- Context window: 258,048 tokens
- Max output: 81,920 tokens
- Input price: $0.195 per 1M tokens
- Output price: $1.56 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-25
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-27b

### Qwen3.5 35B A3B (`qwen/qwen3.5-35b-a3b`)

qwen/qwen3.5-35b-a3b is a language model from Qwen you can call on the OceanToken API at $0.163 per 1M input tokens and $1.30 per 1M output tokens, with a 258K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-35b-a3b
- Type: Text
- Publisher: Qwen
- Context window: 258,048 tokens
- Max output: 235,929 tokens
- Input price: $0.163 per 1M tokens
- Output price: $1.30 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-25
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-35b-a3b

### Qwen3.5 397B A17B (`qwen/qwen3.5-397b-a17b`)

qwen/qwen3.5-397b-a17b is a language model from Qwen you can call on the OceanToken API at $0.39 per 1M input tokens and $2.34 per 1M output tokens, with a 258K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-397b-a17b
- Type: Text
- Publisher: Qwen
- Context window: 258,048 tokens
- Max output: 235,929 tokens
- Input price: $0.39 per 1M tokens
- Output price: $2.34 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-16
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-397b-a17b

### Qwen3.5 9B (`qwen/qwen3.5-9b`)

qwen/qwen3.5-9b is a language model from Qwen you can call on the OceanToken API at $0.10 per 1M input tokens and $0.15 per 1M output tokens, with a 262K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-9b
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 32,768 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.15 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-10
- Scheduled retirement: 2026-10-21
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-9b

### Qwen3.5 Flash 02.23 (`qwen/qwen3.5-flash-02-23`)

qwen/qwen3.5-flash-02-23 is a language model from Qwen you can call on the OceanToken API at $0.065 per 1M input tokens and $0.26 per 1M output tokens, with a 984K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-flash-02-23
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 65,536 tokens
- Input price: $0.065 per 1M tokens
- Output price: $0.26 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-25
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-flash-02-23

### Qwen3.5 Plus 02.15 (`qwen/qwen3.5-plus-02-15`)

qwen/qwen3.5-plus-02-15 is a language model from Qwen you can call on the OceanToken API at $0.26 per 1M input tokens and $1.56 per 1M output tokens, with a 984K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-plus-02-15
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 65,536 tokens
- Input price: $0.26 per 1M tokens
- Output price: $1.56 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-16
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-plus-02-15

### Qwen3.5 Plus 20260420 (`qwen/qwen3.5-plus-20260420`)

qwen/qwen3.5-plus-20260420 is a language model from Qwen you can call on the OceanToken API at $0.30 per 1M input tokens and $1.80 per 1M output tokens, with a 984K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.5-plus-20260420
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 65,536 tokens
- Input price: $0.30 per 1M tokens
- Output price: $1.80 per 1M tokens
- Cache write price: $0.375 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.5-plus-20260420

### Qwen3.6 27B (`qwen/qwen3.6-27b`)

qwen/qwen3.6-27b is a language model from Qwen you can call on the OceanToken API at $0.45 per 1M input tokens and $2.70 per 1M output tokens, with a 258K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.6-27b
- Type: Text
- Publisher: Qwen
- Context window: 258,048 tokens
- Max output: 65,536 tokens
- Input price: $0.45 per 1M tokens
- Output price: $2.70 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.6-27b

### Qwen3.6 35B A3B (`qwen/qwen3.6-35b-a3b`)

qwen/qwen3.6-35b-a3b is a language model from Qwen you can call on the OceanToken API at $0.15 per 1M input tokens and $1.00 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.6-35b-a3b
- Type: Text
- Publisher: Qwen
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.15 per 1M tokens
- Output price: $1.00 per 1M tokens
- Cached input price: $0.05 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.6-35b-a3b

### Qwen3.6 Flash (`qwen/qwen3.6-flash`)

qwen/qwen3.6-flash is a language model from Qwen you can call on the OceanToken API at $0.188 per 1M input tokens and $1.125 per 1M output tokens, with a 984K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.6-flash
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 65,536 tokens
- Input price: $0.188 per 1M tokens
- Output price: $1.125 per 1M tokens
- Cache write price: $0.234 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-27
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.6-flash

### Qwen3.6 Plus (`qwen/qwen3.6-plus`)

qwen/qwen3.6-plus is a language model from Qwen you can call on the OceanToken API at $0.325 per 1M input tokens and $1.95 per 1M output tokens, with a 984K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.6-plus
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 65,536 tokens
- Input price: $0.325 per 1M tokens
- Output price: $1.95 per 1M tokens
- Cache write price: $0.406 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-02
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.6-plus

### Qwen3.7 Flash (`qwen/qwen3.7-flash`)

qwen/qwen3.7-flash is a language model from Qwen you can call on the OceanToken API at $0.03 per 1M input tokens and $0.13 per 1M output tokens, with a 984K-token context window and up to 66K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.7-flash
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 65,536 tokens
- Input price: $0.03 per 1M tokens
- Output price: $0.13 per 1M tokens
- Cached input price: $0.006 per 1M tokens
- Cache write price: $0.038 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-27
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.7-flash

### Qwen3.7 Max (`qwen/qwen3.7-max`)

qwen/qwen3.7-max is a language model from Qwen you can call on the OceanToken API at $1.475 per 1M input tokens and $4.425 per 1M output tokens, with a 984K-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: qwen/qwen3.7-max
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 131,072 tokens
- Input price: $1.475 per 1M tokens
- Output price: $4.425 per 1M tokens
- Cached input price: $0.295 per 1M tokens
- Cache write price: $1.844 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-21
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.7-max

### Qwen3.7 Plus (`qwen/qwen3.7-plus`)

qwen/qwen3.7-plus is a language model from Qwen you can call on the OceanToken API at $0.32 per 1M input tokens and $1.28 per 1M output tokens, with a 984K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.7-plus
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 131,072 tokens
- Input price: $0.32 per 1M tokens
- Output price: $1.28 per 1M tokens
- Cached input price: $0.064 per 1M tokens
- Cache write price: $0.40 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-03
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.7-plus

### Qwen3.8 2.4t A95B (`qwen/qwen3.8-2.4t-a95b`)

qwen/qwen3.8-2.4t-a95b is a language model from Qwen you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 1.05M-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: qwen/qwen3.8-2.4t-a95b
- Type: Text
- Publisher: Qwen
- Context window: 1,048,576 tokens
- Max output: 131,072 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-12
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.8-2.4t-a95b

### Qwen3.8 27B (`qwen/qwen3.8-27b`)

qwen/qwen3.8-27b is a language model from Qwen you can call on the OceanToken API at $0.425 per 1M input tokens and $2.55 per 1M output tokens, with a 1M-token context window and up to 236K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.8-27b
- Type: Text
- Publisher: Qwen
- Context window: 1,000,000 tokens
- Max output: 235,929 tokens
- Input price: $0.425 per 1M tokens
- Output price: $2.55 per 1M tokens
- Cached input price: $0.085 per 1M tokens
- Cache write price: $0.531 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-14
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.8-27b

### Qwen3.8 Flash (`qwen/qwen3.8-flash`)

qwen/qwen3.8-flash is a language model from Qwen you can call on the OceanToken API at $0.15 per 1M input tokens and $0.47 per 1M output tokens, with a 984K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.8-flash
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 131,072 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.47 per 1M tokens
- Cached input price: $0.016 per 1M tokens
- Cache write price: $0.20 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-26
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.8-flash

### Qwen3.8 Max 0902 (`qwen/qwen3.8-max-0902`)

qwen/qwen3.8-max-0902 is a language model from Qwen you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 984K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: qwen/qwen3.8-max-0902
- Type: Text
- Publisher: Qwen
- Context window: 983,616 tokens
- Max output: 131,072 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Cache write price: $2.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-03
- Page: https://docs.oceantoken.ai/models/qwen/qwen3.8-max-0902

## Recraft models

Index: https://docs.oceantoken.ai/models/recraft

### Recraft V3 (`recraft/recraft-v3`)

recraft/recraft-v3 is an image generation model from Recraft you can call on the OceanToken API at $0.04 per generated image; it supports image input.

- Model ID: recraft/recraft-v3
- Type: Image
- Publisher: Recraft
- Price: $0.04 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-07
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v3

### Recraft V4 (`recraft/recraft-v4`)

recraft/recraft-v4 is an image generation model from Recraft you can call on the OceanToken API at $0.04 per generated image; it supports image input.

- Model ID: recraft/recraft-v4
- Type: Image
- Publisher: Recraft
- Price: $0.04 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-07
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4

### Recraft V4 Pro (`recraft/recraft-v4-pro`)

recraft/recraft-v4-pro is an image generation model from Recraft you can call on the OceanToken API at $0.25 per generated image; it supports image input.

- Model ID: recraft/recraft-v4-pro
- Type: Image
- Publisher: Recraft
- Price: $0.25 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-07
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4-pro

### Recraft V4 Pro Vector (`recraft/recraft-v4-pro-vector`)

recraft/recraft-v4-pro-vector is an image generation model from Recraft you can call on the OceanToken API at $0.30 per generated image; it supports image input.

- Model ID: recraft/recraft-v4-pro-vector
- Type: Image
- Publisher: Recraft
- Price: $0.30 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4-pro-vector

### Recraft V4 Styles (`recraft/recraft-v4-styles`)

recraft/recraft-v4-styles is an image generation model from Recraft you can call on the OceanToken API at $0.035 per generated image; it supports image input.

- Model ID: recraft/recraft-v4-styles
- Type: Image
- Publisher: Recraft
- Price: $0.035 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-26
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4-styles

### Recraft V4 Styles Pro (`recraft/recraft-v4-styles-pro`)

recraft/recraft-v4-styles-pro is an image generation model from Recraft you can call on the OceanToken API at $0.10 per generated image; it supports image input.

- Model ID: recraft/recraft-v4-styles-pro
- Type: Image
- Publisher: Recraft
- Price: $0.10 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-26
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4-styles-pro

### Recraft V4 Styles Pro Vector (`recraft/recraft-v4-styles-pro-vector`)

recraft/recraft-v4-styles-pro-vector is an image generation model from Recraft you can call on the OceanToken API at $0.12 per generated image; it supports image input.

- Model ID: recraft/recraft-v4-styles-pro-vector
- Type: Image
- Publisher: Recraft
- Price: $0.12 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-26
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4-styles-pro-vector

### Recraft V4 Styles Vector (`recraft/recraft-v4-styles-vector`)

recraft/recraft-v4-styles-vector is an image generation model from Recraft you can call on the OceanToken API at $0.05 per generated image; it supports image input.

- Model ID: recraft/recraft-v4-styles-vector
- Type: Image
- Publisher: Recraft
- Price: $0.05 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-26
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4-styles-vector

### Recraft V4 Vector (`recraft/recraft-v4-vector`)

recraft/recraft-v4-vector is an image generation model from Recraft you can call on the OceanToken API at $0.08 per generated image; it supports image input.

- Model ID: recraft/recraft-v4-vector
- Type: Image
- Publisher: Recraft
- Price: $0.08 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4-vector

### Recraft V4.1 (`recraft/recraft-v4.1`)

recraft/recraft-v4.1 is an image generation model from Recraft you can call on the OceanToken API at $0.035 per generated image; it supports image input.

- Model ID: recraft/recraft-v4.1
- Type: Image
- Publisher: Recraft
- Price: $0.035 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4.1

### Recraft V4.1 Pro (`recraft/recraft-v4.1-pro`)

recraft/recraft-v4.1-pro is an image generation model from Recraft you can call on the OceanToken API at $0.21 per generated image; it supports image input.

- Model ID: recraft/recraft-v4.1-pro
- Type: Image
- Publisher: Recraft
- Price: $0.21 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4.1-pro

### Recraft V4.1 Pro Vector (`recraft/recraft-v4.1-pro-vector`)

recraft/recraft-v4.1-pro-vector is an image generation model from Recraft you can call on the OceanToken API at $0.30 per generated image; it supports image input.

- Model ID: recraft/recraft-v4.1-pro-vector
- Type: Image
- Publisher: Recraft
- Price: $0.30 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4.1-pro-vector

### Recraft V4.1 Utility (`recraft/recraft-v4.1-utility`)

recraft/recraft-v4.1-utility is an image generation model from Recraft you can call on the OceanToken API at $0.035 per generated image; it supports image input.

- Model ID: recraft/recraft-v4.1-utility
- Type: Image
- Publisher: Recraft
- Price: $0.035 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4.1-utility

### Recraft V4.1 Utility Pro (`recraft/recraft-v4.1-utility-pro`)

recraft/recraft-v4.1-utility-pro is an image generation model from Recraft you can call on the OceanToken API at $0.21 per generated image; it supports image input.

- Model ID: recraft/recraft-v4.1-utility-pro
- Type: Image
- Publisher: Recraft
- Price: $0.21 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4.1-utility-pro

### Recraft V4.1 Vector (`recraft/recraft-v4.1-vector`)

recraft/recraft-v4.1-vector is an image generation model from Recraft you can call on the OceanToken API at $0.08 per generated image; it supports image input.

- Model ID: recraft/recraft-v4.1-vector
- Type: Image
- Publisher: Recraft
- Price: $0.08 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-13
- Page: https://docs.oceantoken.ai/models/recraft/recraft-v4.1-vector

## Rekaai models

Index: https://docs.oceantoken.ai/models/rekaai

### Reka Edge (`rekaai/reka-edge`)

rekaai/reka-edge is a language model from Rekaai you can call on the OceanToken API at $0.10 per 1M input tokens and $0.10 per 1M output tokens, with a 16K-token context window and up to 15K output tokens; it supports tool calling, image input.

- Model ID: rekaai/reka-edge
- Type: Text
- Publisher: Rekaai
- Context window: 16,384 tokens
- Max output: 14,745 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.10 per 1M tokens
- Capabilities: tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-20
- Page: https://docs.oceantoken.ai/models/rekaai/reka-edge

### Reka Flash 3 (`rekaai/reka-flash-3`)

rekaai/reka-flash-3 is a language model from Rekaai you can call on the OceanToken API at $0.10 per 1M input tokens and $0.20 per 1M output tokens, with a 66K-token context window and up to 59K output tokens; it supports reasoning.

- Model ID: rekaai/reka-flash-3
- Type: Text
- Publisher: Rekaai
- Context window: 65,536 tokens
- Max output: 58,982 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.20 per 1M tokens
- Capabilities: reasoning
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-12
- Page: https://docs.oceantoken.ai/models/rekaai/reka-flash-3

## Relace models

Index: https://docs.oceantoken.ai/models/relace

### Relace Apply 3 (`relace/relace-apply-3`)

relace/relace-apply-3 is a language model from Relace you can call on the OceanToken API at $0.85 per 1M input tokens and $1.25 per 1M output tokens, with a 256K-token context window and up to 128K output tokens.

- Model ID: relace/relace-apply-3
- Type: Text
- Publisher: Relace
- Context window: 256,000 tokens
- Max output: 128,000 tokens
- Input price: $0.85 per 1M tokens
- Output price: $1.25 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-26
- Page: https://docs.oceantoken.ai/models/relace/relace-apply-3

### Relace Search (`relace/relace-search`)

relace/relace-search is a language model from Relace you can call on the OceanToken API at $1.00 per 1M input tokens and $3.00 per 1M output tokens, with a 256K-token context window and up to 128K output tokens; it supports tool calling.

- Model ID: relace/relace-search
- Type: Text
- Publisher: Relace
- Context window: 256,000 tokens
- Max output: 128,000 tokens
- Input price: $1.00 per 1M tokens
- Output price: $3.00 per 1M tokens
- Capabilities: tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-08
- Page: https://docs.oceantoken.ai/models/relace/relace-search

## Runway models

Index: https://docs.oceantoken.ai/models/runway

### Aleph 2 (`runway/aleph-2`)

runway/aleph-2 is a video generation model from Runway you can call on the OceanToken API at from $0.28 per second of generated video.

- Model ID: runway/aleph-2
- Type: Video
- Publisher: Runway
- Price: from $0.28 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/runway/aleph-2

### Gen 4.5 (`runway/gen-4.5`)

runway/gen-4.5 is a video generation model from Runway you can call on the OceanToken API at from $0.12 per second of generated video.

- Model ID: runway/gen-4.5
- Type: Video
- Publisher: Runway
- Price: from $0.12 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-29
- Page: https://docs.oceantoken.ai/models/runway/gen-4.5

## Sakana AI models

Index: https://docs.oceantoken.ai/models/sakana

### Fugu Max (`sakana/fugu-max`)

sakana/fugu-max is a language model from Sakana AI you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: sakana/fugu-max
- Type: Text
- Publisher: Sakana AI
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-11
- Page: https://docs.oceantoken.ai/models/sakana/fugu-max

### Fugu Ultra (`sakana/fugu-ultra`)

sakana/fugu-ultra is a language model from Sakana AI you can call on the OceanToken API at $5.00 per 1M input tokens and $30.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: sakana/fugu-ultra
- Type: Text
- Publisher: Sakana AI
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $30.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-24
- Page: https://docs.oceantoken.ai/models/sakana/fugu-ultra

### Fugu Ultra V2 (`sakana/fugu-ultra-v2`)

sakana/fugu-ultra-v2 is a language model from Sakana AI you can call on the OceanToken API at $5.00 per 1M input tokens and $30.00 per 1M output tokens, with a 1M-token context window and up to 128K output tokens; it supports reasoning, tool calling, image input.

- Model ID: sakana/fugu-ultra-v2
- Type: Text
- Publisher: Sakana AI
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Input price: $5.00 per 1M tokens
- Output price: $30.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-11
- Page: https://docs.oceantoken.ai/models/sakana/fugu-ultra-v2

## Sao10k models

Index: https://docs.oceantoken.ai/models/sao10k

### L3 Lunaris 8B (`sao10k/l3-lunaris-8b`)

sao10k/l3-lunaris-8b is a language model from Sao10k you can call on the OceanToken API at $0.04 per 1M input tokens and $0.05 per 1M output tokens, with a 8K-token context window and up to 7K output tokens.

- Model ID: sao10k/l3-lunaris-8b
- Type: Text
- Publisher: Sao10k
- Context window: 8,192 tokens
- Max output: 7,372 tokens
- Input price: $0.04 per 1M tokens
- Output price: $0.05 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-08-13
- Page: https://docs.oceantoken.ai/models/sao10k/l3-lunaris-8b

### L3.1 Euryale 70B (`sao10k/l3.1-euryale-70b`)

sao10k/l3.1-euryale-70b is a language model from Sao10k you can call on the OceanToken API at $0.85 per 1M input tokens and $0.85 per 1M output tokens, with a 131K-token context window and up to 16K output tokens.

- Model ID: sao10k/l3.1-euryale-70b
- Type: Text
- Publisher: Sao10k
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.85 per 1M tokens
- Output price: $0.85 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-08-28
- Page: https://docs.oceantoken.ai/models/sao10k/l3.1-euryale-70b

### L3.3 Euryale 70B (`sao10k/l3.3-euryale-70b`)

sao10k/l3.3-euryale-70b is a language model from Sao10k you can call on the OceanToken API at $0.65 per 1M input tokens and $0.75 per 1M output tokens, with a 131K-token context window and up to 16K output tokens.

- Model ID: sao10k/l3.3-euryale-70b
- Type: Text
- Publisher: Sao10k
- Context window: 131,072 tokens
- Max output: 16,384 tokens
- Input price: $0.65 per 1M tokens
- Output price: $0.75 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-12-18
- Page: https://docs.oceantoken.ai/models/sao10k/l3.3-euryale-70b

## Sentence Transformers models

Index: https://docs.oceantoken.ai/models/sentence-transformers

### All Minilm L12 V2 (`sentence-transformers/all-minilm-l12-v2`)

sentence-transformers/all-minilm-l12-v2 is a text embedding model from Sentence Transformers you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: sentence-transformers/all-minilm-l12-v2
- Type: Embeddings
- Publisher: Sentence Transformers
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/sentence-transformers/all-minilm-l12-v2

### All Minilm L6 V2 (`sentence-transformers/all-minilm-l6-v2`)

sentence-transformers/all-minilm-l6-v2 is a text embedding model from Sentence Transformers you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: sentence-transformers/all-minilm-l6-v2
- Type: Embeddings
- Publisher: Sentence Transformers
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-17
- Page: https://docs.oceantoken.ai/models/sentence-transformers/all-minilm-l6-v2

### All Mpnet Base V2 (`sentence-transformers/all-mpnet-base-v2`)

sentence-transformers/all-mpnet-base-v2 is a text embedding model from Sentence Transformers you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: sentence-transformers/all-mpnet-base-v2
- Type: Embeddings
- Publisher: Sentence Transformers
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-17
- Page: https://docs.oceantoken.ai/models/sentence-transformers/all-mpnet-base-v2

### Multi Qa Mpnet Base Dot V1 (`sentence-transformers/multi-qa-mpnet-base-dot-v1`)

sentence-transformers/multi-qa-mpnet-base-dot-v1 is a text embedding model from Sentence Transformers you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: sentence-transformers/multi-qa-mpnet-base-dot-v1
- Type: Embeddings
- Publisher: Sentence Transformers
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/sentence-transformers/multi-qa-mpnet-base-dot-v1

### Paraphrase Minilm L6 V2 (`sentence-transformers/paraphrase-minilm-l6-v2`)

sentence-transformers/paraphrase-minilm-l6-v2 is a text embedding model from Sentence Transformers you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: sentence-transformers/paraphrase-minilm-l6-v2
- Type: Embeddings
- Publisher: Sentence Transformers
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/sentence-transformers/paraphrase-minilm-l6-v2

## Sesame models

Index: https://docs.oceantoken.ai/models/sesame

### Csm 1B (`sesame/csm-1b`)

sesame/csm-1b is a text-to-speech model from Sesame you can call on the OceanToken API at $0.007 per 1,000 characters.

- Model ID: sesame/csm-1b
- Type: Speech
- Publisher: Sesame
- Price: $0.007 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-23
- Page: https://docs.oceantoken.ai/models/sesame/csm-1b

## Sourceful models

Index: https://docs.oceantoken.ai/models/sourceful

### Riverflow V2 Fast (`sourceful/riverflow-v2-fast`)

sourceful/riverflow-v2-fast is an image generation model from Sourceful you can call on the OceanToken API at $0.04 per generated image; it supports image input.

- Model ID: sourceful/riverflow-v2-fast
- Type: Image
- Publisher: Sourceful
- Price: $0.04 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-02
- Page: https://docs.oceantoken.ai/models/sourceful/riverflow-v2-fast

### Riverflow V2 Pro (`sourceful/riverflow-v2-pro`)

sourceful/riverflow-v2-pro is an image generation model from Sourceful you can call on the OceanToken API at $0.33 per generated image; it supports image input.

- Model ID: sourceful/riverflow-v2-pro
- Type: Image
- Publisher: Sourceful
- Price: $0.33 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-02
- Page: https://docs.oceantoken.ai/models/sourceful/riverflow-v2-pro

### Riverflow V2.5 Fast (`sourceful/riverflow-v2.5-fast`)

sourceful/riverflow-v2.5-fast is an image generation model from Sourceful you can call on the OceanToken API at $0.021 per generated image; it supports image input.

- Model ID: sourceful/riverflow-v2.5-fast
- Type: Image
- Publisher: Sourceful
- Price: $0.021 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-04
- Page: https://docs.oceantoken.ai/models/sourceful/riverflow-v2.5-fast

### Riverflow V2.5 Pro (`sourceful/riverflow-v2.5-pro`)

sourceful/riverflow-v2.5-pro is an image generation model from Sourceful you can call on the OceanToken API at $0.17 per generated image; it supports image input.

- Model ID: sourceful/riverflow-v2.5-pro
- Type: Image
- Publisher: Sourceful
- Price: $0.17 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-04
- Page: https://docs.oceantoken.ai/models/sourceful/riverflow-v2.5-pro

## StepFun models

Index: https://docs.oceantoken.ai/models/stepfun

### Step-3.5 Flash (`stepfun/step-3.5-flash`)

stepfun/step-3.5-flash is a language model from StepFun you can call on the OceanToken API at $0.10 per 1M input tokens and $0.30 per 1M output tokens, with a 262K-token context window and up to 66K output tokens; it supports reasoning, tool calling.

- Model ID: stepfun/step-3.5-flash
- Type: Text
- Publisher: StepFun
- Context window: 262,144 tokens
- Max output: 65,536 tokens
- Input price: $0.10 per 1M tokens
- Output price: $0.30 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-29
- Page: https://docs.oceantoken.ai/models/stepfun/step-3.5-flash

### Step-3.7 Flash (`stepfun/step-3.7-flash`)

stepfun/step-3.7-flash is a language model from StepFun you can call on the OceanToken API at $0.20 per 1M input tokens and $1.15 per 1M output tokens, with a 262K-token context window and up to 230K output tokens; it supports reasoning, tool calling, image input.

- Model ID: stepfun/step-3.7-flash
- Type: Text
- Publisher: StepFun
- Context window: 262,144 tokens
- Max output: 230,400 tokens
- Input price: $0.20 per 1M tokens
- Output price: $1.15 per 1M tokens
- Cached input price: $0.04 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-28
- Page: https://docs.oceantoken.ai/models/stepfun/step-3.7-flash

## Tencent models

Index: https://docs.oceantoken.ai/models/tencent

### Hunyuan A13B Instruct (`tencent/hunyuan-a13b-instruct`)

tencent/hunyuan-a13b-instruct is a language model from Tencent you can call on the OceanToken API at $0.14 per 1M input tokens and $0.57 per 1M output tokens, with a 131K-token context window and up to 118K output tokens; it supports reasoning.

- Model ID: tencent/hunyuan-a13b-instruct
- Type: Text
- Publisher: Tencent
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.14 per 1M tokens
- Output price: $0.57 per 1M tokens
- Capabilities: reasoning
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-08
- Page: https://docs.oceantoken.ai/models/tencent/hunyuan-a13b-instruct

### Hy Mt2 1.8b (`tencent/hy-mt2-1.8b`)

tencent/hy-mt2-1.8b is a language model from Tencent you can call on the OceanToken API at $0.044 per 1M input tokens and $0.177 per 1M output tokens, with a 8K-token context window and up to 4K output tokens.

- Model ID: tencent/hy-mt2-1.8b
- Type: Text
- Publisher: Tencent
- Context window: 8,192 tokens
- Max output: 4,096 tokens
- Input price: $0.044 per 1M tokens
- Output price: $0.177 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-20
- Page: https://docs.oceantoken.ai/models/tencent/hy-mt2-1.8b

### Hy Mt2 30B A3B (`tencent/hy-mt2-30b-a3b`)

tencent/hy-mt2-30b-a3b is a language model from Tencent you can call on the OceanToken API at $0.074 per 1M input tokens and $0.295 per 1M output tokens, with a 8K-token context window and up to 4K output tokens.

- Model ID: tencent/hy-mt2-30b-a3b
- Type: Text
- Publisher: Tencent
- Context window: 8,192 tokens
- Max output: 4,096 tokens
- Input price: $0.074 per 1M tokens
- Output price: $0.295 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-20
- Page: https://docs.oceantoken.ai/models/tencent/hy-mt2-30b-a3b

### Hy Mt2 7B (`tencent/hy-mt2-7b`)

tencent/hy-mt2-7b is a language model from Tencent you can call on the OceanToken API at $0.074 per 1M input tokens and $0.295 per 1M output tokens, with a 8K-token context window and up to 4K output tokens.

- Model ID: tencent/hy-mt2-7b
- Type: Text
- Publisher: Tencent
- Context window: 8,192 tokens
- Max output: 4,096 tokens
- Input price: $0.074 per 1M tokens
- Output price: $0.295 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-19
- Page: https://docs.oceantoken.ai/models/tencent/hy-mt2-7b

### Hy3 (`tencent/hy3`)

tencent/hy3 is a language model from Tencent you can call on the OceanToken API at $0.132 per 1M input tokens and $0.528 per 1M output tokens, with a 262K-token context window and up to 128K output tokens; it supports reasoning, tool calling.

- Model ID: tencent/hy3
- Type: Text
- Publisher: Tencent
- Context window: 262,144 tokens
- Max output: 128,000 tokens
- Input price: $0.132 per 1M tokens
- Output price: $0.528 per 1M tokens
- Cached input price: $0.033 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-06
- Page: https://docs.oceantoken.ai/models/tencent/hy3

### Hy3 Preview (`tencent/hy3-preview`)

tencent/hy3-preview is a language model from Tencent you can call on the OceanToken API at $0.18 per 1M input tokens and $0.60 per 1M output tokens, with a 262K-token context window and up to 236K output tokens; it supports reasoning, tool calling.

- Model ID: tencent/hy3-preview
- Type: Text
- Publisher: Tencent
- Context window: 262,144 tokens
- Max output: 235,929 tokens
- Input price: $0.18 per 1M tokens
- Output price: $0.60 per 1M tokens
- Cached input price: $0.06 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-22
- Page: https://docs.oceantoken.ai/models/tencent/hy3-preview

### Hy4 Preview (`tencent/hy4-preview`)

tencent/hy4-preview is a language model from Tencent you can call on the OceanToken API at $0.834 per 1M input tokens and $2.501 per 1M output tokens, with a 1.05M-token context window and up to 64K output tokens; it supports reasoning, tool calling.

- Model ID: tencent/hy4-preview
- Type: Text
- Publisher: Tencent
- Context window: 1,048,576 tokens
- Max output: 64,000 tokens
- Input price: $0.834 per 1M tokens
- Output price: $2.501 per 1M tokens
- Cached input price: $0.042 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-28
- Page: https://docs.oceantoken.ai/models/tencent/hy4-preview

## Thedrummer models

Index: https://docs.oceantoken.ai/models/thedrummer

### Cydonia 24B V4.1 (`thedrummer/cydonia-24b-v4.1`)

thedrummer/cydonia-24b-v4.1 is a language model from Thedrummer you can call on the OceanToken API at $0.30 per 1M input tokens and $0.50 per 1M output tokens, with a 131K-token context window and up to 118K output tokens.

- Model ID: thedrummer/cydonia-24b-v4.1
- Type: Text
- Publisher: Thedrummer
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.30 per 1M tokens
- Output price: $0.50 per 1M tokens
- Cached input price: $0.15 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-27
- Page: https://docs.oceantoken.ai/models/thedrummer/cydonia-24b-v4.1

### Skyfall 36B V2 (`thedrummer/skyfall-36b-v2`)

thedrummer/skyfall-36b-v2 is a language model from Thedrummer you can call on the OceanToken API at $0.55 per 1M input tokens and $0.80 per 1M output tokens, with a 33K-token context window and up to 29K output tokens.

- Model ID: thedrummer/skyfall-36b-v2
- Type: Text
- Publisher: Thedrummer
- Context window: 32,768 tokens
- Max output: 29,491 tokens
- Input price: $0.55 per 1M tokens
- Output price: $0.80 per 1M tokens
- Cached input price: $0.25 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-03-10
- Page: https://docs.oceantoken.ai/models/thedrummer/skyfall-36b-v2

### Unslopnemo 12B (`thedrummer/unslopnemo-12b`)

thedrummer/unslopnemo-12b is a language model from Thedrummer you can call on the OceanToken API at $0.40 per 1M input tokens and $0.40 per 1M output tokens, with a 1.02M-token context window and up to 819K output tokens.

- Model ID: thedrummer/unslopnemo-12b
- Type: Text
- Publisher: Thedrummer
- Context window: 1,024,000 tokens
- Max output: 819,200 tokens
- Input price: $0.40 per 1M tokens
- Output price: $0.40 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2024-11-08
- Page: https://docs.oceantoken.ai/models/thedrummer/unslopnemo-12b

## Thenlper models

Index: https://docs.oceantoken.ai/models/thenlper

### Gte Base (`thenlper/gte-base`)

thenlper/gte-base is a text embedding model from Thenlper you can call on the OceanToken API at $0.005 per 1M input tokens, with a 1K-token context window.

- Model ID: thenlper/gte-base
- Type: Embeddings
- Publisher: Thenlper
- Context window: 512 tokens
- Input price: $0.005 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/thenlper/gte-base

### Gte Large (`thenlper/gte-large`)

thenlper/gte-large is a text embedding model from Thenlper you can call on the OceanToken API at $0.01 per 1M input tokens, with a 1K-token context window.

- Model ID: thenlper/gte-large
- Type: Embeddings
- Publisher: Thenlper
- Context window: 512 tokens
- Input price: $0.01 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2025-11-18
- Page: https://docs.oceantoken.ai/models/thenlper/gte-large

## Thinkingmachines models

Index: https://docs.oceantoken.ai/models/thinkingmachines

### Inkling (`thinkingmachines/inkling`)

thinkingmachines/inkling is a language model from Thinkingmachines you can call on the OceanToken API at $0.95 per 1M input tokens and $4.05 per 1M output tokens, with a 524K-token context window and up to 472K output tokens; it supports reasoning, tool calling, image input.

- Model ID: thinkingmachines/inkling
- Type: Text
- Publisher: Thinkingmachines
- Context window: 524,288 tokens
- Max output: 471,859 tokens
- Input price: $0.95 per 1M tokens
- Output price: $4.05 per 1M tokens
- Cached input price: $0.16 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-17
- Page: https://docs.oceantoken.ai/models/thinkingmachines/inkling

### Inkling Small (`thinkingmachines/inkling-small`)

thinkingmachines/inkling-small is a language model from Thinkingmachines you can call on the OceanToken API at $0.45 per 1M input tokens and $1.20 per 1M output tokens, with a 524K-token context window and up to 262K output tokens; it supports reasoning, tool calling, image input.

- Model ID: thinkingmachines/inkling-small
- Type: Text
- Publisher: Thinkingmachines
- Context window: 524,288 tokens
- Max output: 262,144 tokens
- Input price: $0.45 per 1M tokens
- Output price: $1.20 per 1M tokens
- Cached input price: $0.10 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-30
- Page: https://docs.oceantoken.ai/models/thinkingmachines/inkling-small

## Typesafe models

Index: https://docs.oceantoken.ai/models/typesafe

### Jev 1.13 (`typesafe/jev-1.13`)

typesafe/jev-1.13 is a decision model from Typesafe you can call on the OceanToken API at $0.042 per 1M input tokens.

- Model ID: typesafe/jev-1.13
- Type: Decisions
- Publisher: Typesafe
- Input price: $0.042 per 1M tokens
- API shape: OpenAI-compatible
- In the catalog since: 2026-09-18
- Page: https://docs.oceantoken.ai/models/typesafe/jev-1.13

## Undi95 models

Index: https://docs.oceantoken.ai/models/undi95

### Remm Slerp L2 13B (`undi95/remm-slerp-l2-13b`)

undi95/remm-slerp-l2-13b is a language model from Undi95 you can call on the OceanToken API at $0.35 per 1M input tokens and $0.65 per 1M output tokens, with a 6K-token context window and up to 6K output tokens.

- Model ID: undi95/remm-slerp-l2-13b
- Type: Text
- Publisher: Undi95
- Context window: 6,144 tokens
- Max output: 5,529 tokens
- Input price: $0.35 per 1M tokens
- Output price: $0.65 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2023-07-22
- Page: https://docs.oceantoken.ai/models/undi95/remm-slerp-l2-13b

## Upstage models

Index: https://docs.oceantoken.ai/models/upstage

### Solar Pro 3 (`upstage/solar-pro-3`)

upstage/solar-pro-3 is a language model from Upstage you can call on the OceanToken API at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 131K-token context window and up to 118K output tokens; it supports reasoning, tool calling.

- Model ID: upstage/solar-pro-3
- Type: Text
- Publisher: Upstage
- Context window: 131,072 tokens
- Max output: 117,964 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.60 per 1M tokens
- Cached input price: $0.015 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-27
- Page: https://docs.oceantoken.ai/models/upstage/solar-pro-3

### Solar Pro4 (`upstage/solar-pro4`)

upstage/solar-pro4 is a language model from Upstage you can call on the OceanToken API at $0.09 per 1M input tokens and $0.36 per 1M output tokens, with a 524K-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: upstage/solar-pro4
- Type: Text
- Publisher: Upstage
- Context window: 524,288 tokens
- Max output: 131,072 tokens
- Input price: $0.09 per 1M tokens
- Output price: $0.36 per 1M tokens
- Cached input price: $0.018 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-10
- Page: https://docs.oceantoken.ai/models/upstage/solar-pro4

## Voyage AI models

Index: https://docs.oceantoken.ai/models/voyageai

### Rerank 2.5 (`voyageai/rerank-2.5`)

voyageai/rerank-2.5 is a reranking model from Voyage AI you can call on the OceanToken API at $0.05 per 1M input tokens.

- Model ID: voyageai/rerank-2.5
- Type: Rerank
- Publisher: Voyage AI
- Input price: $0.05 per 1M tokens
- Endpoint: /v1/rerank
- API shape: Cohere rerank
- In the catalog since: 2026-07-27
- Page: https://docs.oceantoken.ai/models/voyageai/rerank-2.5

### Rerank 2.5 Lite (`voyageai/rerank-2.5-lite`)

voyageai/rerank-2.5-lite is a reranking model from Voyage AI you can call on the OceanToken API at $0.02 per 1M input tokens.

- Model ID: voyageai/rerank-2.5-lite
- Type: Rerank
- Publisher: Voyage AI
- Input price: $0.02 per 1M tokens
- Endpoint: /v1/rerank
- API shape: Cohere rerank
- In the catalog since: 2026-07-27
- Page: https://docs.oceantoken.ai/models/voyageai/rerank-2.5-lite

### Voyage 4 (`voyageai/voyage-4`)

voyageai/voyage-4 is a text embedding model from Voyage AI you can call on the OceanToken API at $0.06 per 1M input tokens, with a 32K-token context window.

- Model ID: voyageai/voyage-4
- Type: Embeddings
- Publisher: Voyage AI
- Context window: 32,000 tokens
- Input price: $0.06 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-27
- Page: https://docs.oceantoken.ai/models/voyageai/voyage-4

### Voyage 4 Large (`voyageai/voyage-4-large`)

voyageai/voyage-4-large is a text embedding model from Voyage AI you can call on the OceanToken API at $0.12 per 1M input tokens, with a 32K-token context window.

- Model ID: voyageai/voyage-4-large
- Type: Embeddings
- Publisher: Voyage AI
- Context window: 32,000 tokens
- Input price: $0.12 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-27
- Page: https://docs.oceantoken.ai/models/voyageai/voyage-4-large

### Voyage 4 Lite (`voyageai/voyage-4-lite`)

voyageai/voyage-4-lite is a text embedding model from Voyage AI you can call on the OceanToken API at $0.02 per 1M input tokens, with a 32K-token context window.

- Model ID: voyageai/voyage-4-lite
- Type: Embeddings
- Publisher: Voyage AI
- Context window: 32,000 tokens
- Input price: $0.02 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-27
- Page: https://docs.oceantoken.ai/models/voyageai/voyage-4-lite

### Voyage Code 4 (`voyageai/voyage-code-4`)

voyageai/voyage-code-4 is a text embedding model from Voyage AI you can call on the OceanToken API at $0.12 per 1M input tokens, with a 32K-token context window.

- Model ID: voyageai/voyage-code-4
- Type: Embeddings
- Publisher: Voyage AI
- Context window: 32,000 tokens
- Input price: $0.12 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-13
- Page: https://docs.oceantoken.ai/models/voyageai/voyage-code-4

### Voyage Multimodal 3.5 (`voyageai/voyage-multimodal-3.5`)

voyageai/voyage-multimodal-3.5 is a text embedding model from Voyage AI you can call on the OceanToken API at $0.12 per 1M input tokens, with a 32K-token context window.

- Model ID: voyageai/voyage-multimodal-3.5
- Type: Embeddings
- Publisher: Voyage AI
- Context window: 32,000 tokens
- Input price: $0.12 per 1M tokens
- Endpoint: /v1/embeddings
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-27
- Page: https://docs.oceantoken.ai/models/voyageai/voyage-multimodal-3.5

## Writer models

Index: https://docs.oceantoken.ai/models/writer

### Palmyra X5 (`writer/palmyra-x5`)

writer/palmyra-x5 is a language model from Writer you can call on the OceanToken API at $0.60 per 1M input tokens and $6.00 per 1M output tokens, with a 1.04M-token context window and up to 8K output tokens.

- Model ID: writer/palmyra-x5
- Type: Text
- Publisher: Writer
- Context window: 1,040,000 tokens
- Max output: 8,192 tokens
- Input price: $0.60 per 1M tokens
- Output price: $6.00 per 1M tokens
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-21
- Page: https://docs.oceantoken.ai/models/writer/palmyra-x5

## xAI models

Index: https://docs.oceantoken.ai/models/x-ai

### Grok 4.20 (`x-ai/grok-4.20`)

x-ai/grok-4.20 is a language model from xAI you can call on the OceanToken API at $1.25 per 1M input tokens and $2.50 per 1M output tokens, with a 2M-token context window and up to 1.8M output tokens; it supports reasoning, tool calling, image input.

- Model ID: x-ai/grok-4.20
- Type: Text
- Publisher: xAI
- Context window: 2,000,000 tokens
- Max output: 1,800,000 tokens
- Input price: $1.25 per 1M tokens
- Output price: $2.50 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-31
- Page: https://docs.oceantoken.ai/models/x-ai/grok-4.20

### Grok 4.20 Multi Agent (`x-ai/grok-4.20-multi-agent`)

x-ai/grok-4.20-multi-agent is a language model from xAI you can call on the OceanToken API at $1.25 per 1M input tokens and $2.50 per 1M output tokens, with a 2M-token context window and up to 1.8M output tokens; it supports reasoning, image input.

- Model ID: x-ai/grok-4.20-multi-agent
- Type: Text
- Publisher: xAI
- Context window: 2,000,000 tokens
- Max output: 1,800,000 tokens
- Input price: $1.25 per 1M tokens
- Output price: $2.50 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: reasoning, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-31
- Page: https://docs.oceantoken.ai/models/x-ai/grok-4.20-multi-agent

### Grok 4.3 (`x-ai/grok-4.3`)

x-ai/grok-4.3 is a language model from xAI you can call on the OceanToken API at $1.25 per 1M input tokens and $2.50 per 1M output tokens, with a 1M-token context window and up to 900K output tokens; it supports reasoning, tool calling, image input.

- Model ID: x-ai/grok-4.3
- Type: Text
- Publisher: xAI
- Context window: 1,000,000 tokens
- Max output: 900,000 tokens
- Input price: $1.25 per 1M tokens
- Output price: $2.50 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-30
- Page: https://docs.oceantoken.ai/models/x-ai/grok-4.3

### Grok 4.5 (`x-ai/grok-4.5`)

x-ai/grok-4.5 is a language model from xAI you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 500K-token context window and up to 450K output tokens; it supports reasoning, tool calling, image input.

- Model ID: x-ai/grok-4.5
- Type: Text
- Publisher: xAI
- Context window: 500,000 tokens
- Max output: 450,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.30 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-08
- Page: https://docs.oceantoken.ai/models/x-ai/grok-4.5

### Grok 4.6 (`x-ai/grok-4.6`)

x-ai/grok-4.6 is a language model from xAI you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 500K-token context window and up to 450K output tokens; it supports reasoning, tool calling, image input.

- Model ID: x-ai/grok-4.6
- Type: Text
- Publisher: xAI
- Context window: 500,000 tokens
- Max output: 450,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-12
- Page: https://docs.oceantoken.ai/models/x-ai/grok-4.6

### Grok Build 0.1 (`x-ai/grok-build-0.1`)

x-ai/grok-build-0.1 is a language model from xAI you can call on the OceanToken API at $1.00 per 1M input tokens and $2.00 per 1M output tokens, with a 256K-token context window and up to 230K output tokens; it supports reasoning, tool calling, image input.

- Model ID: x-ai/grok-build-0.1
- Type: Text
- Publisher: xAI
- Context window: 256,000 tokens
- Max output: 230,400 tokens
- Input price: $1.00 per 1M tokens
- Output price: $2.00 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-20
- Page: https://docs.oceantoken.ai/models/x-ai/grok-build-0.1

### Grok Imagine Image 2.0 (`x-ai/grok-imagine-image-2.0`)

x-ai/grok-imagine-image-2.0 is an image generation model from xAI you can call on the OceanToken API at $0.08 per generated image; it supports image input.

- Model ID: x-ai/grok-imagine-image-2.0
- Type: Image
- Publisher: xAI
- Price: $0.08 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-11
- Page: https://docs.oceantoken.ai/models/x-ai/grok-imagine-image-2.0

### Grok Imagine Image Quality (`x-ai/grok-imagine-image-quality`)

x-ai/grok-imagine-image-quality is an image generation model from xAI you can call on the OceanToken API at $0.07 per generated image; it supports image input.

- Model ID: x-ai/grok-imagine-image-quality
- Type: Image
- Publisher: xAI
- Price: $0.07 per image
- Endpoint: /v1/images/generations, /v1/images/edits
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-18
- Page: https://docs.oceantoken.ai/models/x-ai/grok-imagine-image-quality

### Grok Imagine Video (`x-ai/grok-imagine-video`)

x-ai/grok-imagine-video is a video generation model from xAI you can call on the OceanToken API at from $0.05 per second of generated video.

- Model ID: x-ai/grok-imagine-video
- Type: Video
- Publisher: xAI
- Price: from $0.05 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-18
- Page: https://docs.oceantoken.ai/models/x-ai/grok-imagine-video

### Grok Imagine Video 1.5 (`x-ai/grok-imagine-video-1.5`)

x-ai/grok-imagine-video-1.5 is a video generation model from xAI you can call on the OceanToken API at from $0.08 per second of generated video.

- Model ID: x-ai/grok-imagine-video-1.5
- Type: Video
- Publisher: xAI
- Price: from $0.08 per second of video
- Endpoint: /v1/videos
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-20
- Page: https://docs.oceantoken.ai/models/x-ai/grok-imagine-video-1.5

### Grok Latest (`x-ai/grok-latest`)

x-ai/grok-latest is a language model from xAI you can call on the OceanToken API at $2.00 per 1M input tokens and $6.00 per 1M output tokens, with a 500K-token context window and up to 450K output tokens; it supports reasoning, tool calling, image input.

- Model ID: x-ai/grok-latest
- Type: Text
- Publisher: xAI
- Context window: 500,000 tokens
- Max output: 450,000 tokens
- Input price: $2.00 per 1M tokens
- Output price: $6.00 per 1M tokens
- Cached input price: $0.50 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: x-ai/grok-4.7
- In the catalog since: 2026-07-08
- Page: https://docs.oceantoken.ai/models/x-ai/grok-latest

### Grok STT 1.0 (`x-ai/grok-stt-1.0`)

x-ai/grok-stt-1.0 is a speech-to-text model from xAI you can call on the OceanToken API at $0.00167 per minute of audio.

- Model ID: x-ai/grok-stt-1.0
- Type: Transcription
- Publisher: xAI
- Price: $0.00167 per minute of audio
- Endpoint: /v1/audio/transcriptions
- API shape: OpenAI-compatible
- In the catalog since: 2026-07-23
- Page: https://docs.oceantoken.ai/models/x-ai/grok-stt-1.0

### Grok Voice TTS 1.0 (`x-ai/grok-voice-tts-1.0`)

x-ai/grok-voice-tts-1.0 is a text-to-speech model from xAI you can call on the OceanToken API at $0.015 per 1,000 characters.

- Model ID: x-ai/grok-voice-tts-1.0
- Type: Speech
- Publisher: xAI
- Price: $0.015 per 1,000 characters of input text
- Endpoint: /v1/audio/speech
- API shape: OpenAI-compatible
- In the catalog since: 2026-05-15
- Page: https://docs.oceantoken.ai/models/x-ai/grok-voice-tts-1.0

## Xiaomi models

Index: https://docs.oceantoken.ai/models/xiaomi

### MiMo V2.5 (`xiaomi/mimo-v2.5`)

xiaomi/mimo-v2.5 is a language model from Xiaomi you can call on the OceanToken API at $0.14 per 1M input tokens and $0.28 per 1M output tokens, with a 1.05M-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: xiaomi/mimo-v2.5
- Type: Text
- Publisher: Xiaomi
- Context window: 1,050,000 tokens
- Max output: 131,072 tokens
- Input price: $0.14 per 1M tokens
- Output price: $0.28 per 1M tokens
- Cached input price: $0.0028 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-22
- Scheduled retirement: 2026-10-21
- Page: https://docs.oceantoken.ai/models/xiaomi/mimo-v2.5

### MiMo V2.5 Pro (`xiaomi/mimo-v2.5-pro`)

xiaomi/mimo-v2.5-pro is a language model from Xiaomi you can call on the OceanToken API at $0.435 per 1M input tokens and $0.87 per 1M output tokens, with a 1.05M-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: xiaomi/mimo-v2.5-pro
- Type: Text
- Publisher: Xiaomi
- Context window: 1,050,000 tokens
- Max output: 131,072 tokens
- Input price: $0.435 per 1M tokens
- Output price: $0.87 per 1M tokens
- Cached input price: $0.0036 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-22
- Scheduled retirement: 2026-10-21
- Page: https://docs.oceantoken.ai/models/xiaomi/mimo-v2.5-pro

## Z.ai models

Index: https://docs.oceantoken.ai/models/z-ai

### GLM-4.5 (`z-ai/glm-4.5`)

z-ai/glm-4.5 is a language model from Z.ai you can call on the OceanToken API at $0.60 per 1M input tokens and $2.20 per 1M output tokens, with a 131K-token context window and up to 98K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-4.5
- Type: Text
- Publisher: Z.ai
- Context window: 131,072 tokens
- Max output: 98,304 tokens
- Input price: $0.60 per 1M tokens
- Output price: $2.20 per 1M tokens
- Cached input price: $0.11 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-25
- Scheduled retirement: 2026-12-31
- Page: https://docs.oceantoken.ai/models/z-ai/glm-4.5

### GLM-4.5 Air (`z-ai/glm-4.5-air`)

z-ai/glm-4.5-air is a language model from Z.ai you can call on the OceanToken API at $0.20 per 1M input tokens and $1.10 per 1M output tokens, with a 131K-token context window and up to 98K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-4.5-air
- Type: Text
- Publisher: Z.ai
- Context window: 131,072 tokens
- Max output: 98,304 tokens
- Input price: $0.20 per 1M tokens
- Output price: $1.10 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-07-25
- Page: https://docs.oceantoken.ai/models/z-ai/glm-4.5-air

### GLM-4.5v (`z-ai/glm-4.5v`)

z-ai/glm-4.5v is a language model from Z.ai you can call on the OceanToken API at $0.60 per 1M input tokens and $1.80 per 1M output tokens, with a 66K-token context window and up to 16K output tokens; it supports reasoning, tool calling, image input.

- Model ID: z-ai/glm-4.5v
- Type: Text
- Publisher: Z.ai
- Context window: 65,536 tokens
- Max output: 16,384 tokens
- Input price: $0.60 per 1M tokens
- Output price: $1.80 per 1M tokens
- Cached input price: $0.11 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-08-11
- Page: https://docs.oceantoken.ai/models/z-ai/glm-4.5v

### GLM-4.6 (`z-ai/glm-4.6`)

z-ai/glm-4.6 is a language model from Z.ai you can call on the OceanToken API at $0.60 per 1M input tokens and $2.20 per 1M output tokens, with a 205K-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-4.6
- Type: Text
- Publisher: Z.ai
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Input price: $0.60 per 1M tokens
- Output price: $2.20 per 1M tokens
- Cached input price: $0.11 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-09-30
- Page: https://docs.oceantoken.ai/models/z-ai/glm-4.6

### GLM-4.6v (`z-ai/glm-4.6v`)

z-ai/glm-4.6v is a language model from Z.ai you can call on the OceanToken API at $0.30 per 1M input tokens and $0.90 per 1M output tokens, with a 131K-token context window and up to 33K output tokens; it supports reasoning, tool calling, image input.

- Model ID: z-ai/glm-4.6v
- Type: Text
- Publisher: Z.ai
- Context window: 131,072 tokens
- Max output: 32,768 tokens
- Input price: $0.30 per 1M tokens
- Output price: $0.90 per 1M tokens
- Cached input price: $0.05 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-08
- Page: https://docs.oceantoken.ai/models/z-ai/glm-4.6v

### GLM-4.7 (`z-ai/glm-4.7`)

z-ai/glm-4.7 is a language model from Z.ai you can call on the OceanToken API at $0.60 per 1M input tokens and $2.20 per 1M output tokens, with a 205K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: z-ai/glm-4.7
- Type: Text
- Publisher: Z.ai
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Input price: $0.60 per 1M tokens
- Output price: $2.20 per 1M tokens
- Cached input price: $0.11 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2025-12-22
- Scheduled retirement: 2026-12-31
- Page: https://docs.oceantoken.ai/models/z-ai/glm-4.7

### GLM-4.7 Flash (`z-ai/glm-4.7-flash`)

z-ai/glm-4.7-flash is a language model from Z.ai you can call on the OceanToken API at $0.0605 per 1M input tokens and $0.40 per 1M output tokens, with a 200K-token context window and up to 118K output tokens; it supports reasoning, tool calling, image input.

- Model ID: z-ai/glm-4.7-flash
- Type: Text
- Publisher: Z.ai
- Context window: 200,000 tokens
- Max output: 117,964 tokens
- Input price: $0.0605 per 1M tokens
- Output price: $0.40 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-01-19
- Page: https://docs.oceantoken.ai/models/z-ai/glm-4.7-flash

### GLM-5 (`z-ai/glm-5`)

z-ai/glm-5 is a language model from Z.ai you can call on the OceanToken API at $1.00 per 1M input tokens and $3.20 per 1M output tokens, with a 205K-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-5
- Type: Text
- Publisher: Z.ai
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Input price: $1.00 per 1M tokens
- Output price: $3.20 per 1M tokens
- Cached input price: $0.20 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-02-11
- Page: https://docs.oceantoken.ai/models/z-ai/glm-5

### GLM-5 Turbo (`z-ai/glm-5-turbo`)

z-ai/glm-5-turbo is a language model from Z.ai you can call on the OceanToken API at $1.20 per 1M input tokens and $4.00 per 1M output tokens, with a 203K-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-5-turbo
- Type: Text
- Publisher: Z.ai
- Context window: 202,752 tokens
- Max output: 131,072 tokens
- Input price: $1.20 per 1M tokens
- Output price: $4.00 per 1M tokens
- Cached input price: $0.24 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-03-15
- Page: https://docs.oceantoken.ai/models/z-ai/glm-5-turbo

### GLM-5.1 (`z-ai/glm-5.1`)

z-ai/glm-5.1 is a language model from Z.ai you can call on the OceanToken API at $1.40 per 1M input tokens and $4.40 per 1M output tokens, with a 205K-token context window and up to 128K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-5.1
- Type: Text
- Publisher: Z.ai
- Context window: 204,800 tokens
- Max output: 128,000 tokens
- Input price: $1.40 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.26 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-07
- Page: https://docs.oceantoken.ai/models/z-ai/glm-5.1

### GLM-5.2 (`z-ai/glm-5.2`)

z-ai/glm-5.2 is a language model from Z.ai you can call on the OceanToken API at $1.40 per 1M input tokens and $4.40 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-5.2
- Type: Text
- Publisher: Z.ai
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $1.40 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.26 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-06-16
- Page: https://docs.oceantoken.ai/models/z-ai/glm-5.2

### GLM-5.3 (`z-ai/glm-5.3`)

z-ai/glm-5.3 is a language model from Z.ai you can call on the OceanToken API at $1.40 per 1M input tokens and $4.40 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-5.3
- Type: Text
- Publisher: Z.ai
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $1.40 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.26 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-18
- Page: https://docs.oceantoken.ai/models/z-ai/glm-5.3

### GLM-5.3 Flash (`z-ai/glm-5.3-flash`)

z-ai/glm-5.3-flash is a language model from Z.ai you can call on the OceanToken API at $0.15 per 1M input tokens and $0.50 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: z-ai/glm-5.3-flash
- Type: Text
- Publisher: Z.ai
- Context window: 1,048,576 tokens
- Max output: 943,717 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.50 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-26
- Page: https://docs.oceantoken.ai/models/z-ai/glm-5.3-flash

### GLM-5v Turbo (`z-ai/glm-5v-turbo`)

z-ai/glm-5v-turbo is a language model from Z.ai you can call on the OceanToken API at $1.20 per 1M input tokens and $4.00 per 1M output tokens, with a 203K-token context window and up to 131K output tokens; it supports reasoning, tool calling, image input.

- Model ID: z-ai/glm-5v-turbo
- Type: Text
- Publisher: Z.ai
- Context window: 202,752 tokens
- Max output: 131,072 tokens
- Input price: $1.20 per 1M tokens
- Output price: $4.00 per 1M tokens
- Cached input price: $0.24 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-04-01
- Page: https://docs.oceantoken.ai/models/z-ai/glm-5v-turbo

### GLM Flash Latest (`z-ai/glm-flash-latest`)

z-ai/glm-flash-latest is a language model from Z.ai you can call on the OceanToken API at $0.15 per 1M input tokens and $0.50 per 1M output tokens, with a 1.05M-token context window and up to 944K output tokens; it supports reasoning, tool calling, image input.

- Model ID: z-ai/glm-flash-latest
- Type: Text
- Publisher: Z.ai
- Context window: 1,048,576 tokens
- Max output: 943,718 tokens
- Input price: $0.15 per 1M tokens
- Output price: $0.50 per 1M tokens
- Cached input price: $0.03 per 1M tokens
- Capabilities: reasoning, tool calling, image input
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: z-ai/glm-5.3-flash
- In the catalog since: 2026-08-27
- Page: https://docs.oceantoken.ai/models/z-ai/glm-flash-latest

### GLM Latest (`z-ai/glm-latest`)

z-ai/glm-latest is a language model from Z.ai you can call on the OceanToken API at $1.40 per 1M input tokens and $4.40 per 1M output tokens, with a 1.05M-token context window and up to 131K output tokens; it supports reasoning, tool calling.

- Model ID: z-ai/glm-latest
- Type: Text
- Publisher: Z.ai
- Context window: 1,048,576 tokens
- Max output: 131,072 tokens
- Input price: $1.40 per 1M tokens
- Output price: $4.40 per 1M tokens
- Cached input price: $0.26 per 1M tokens
- Capabilities: reasoning, tool calling
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- Alias of: z-ai/glm-5.3
- In the catalog since: 2026-08-19
- Page: https://docs.oceantoken.ai/models/z-ai/glm-latest

## Other

### Smart Router (`smart-router`)

smart-router is OceanToken's router: it picks a language model for each request, and each request is billed at the listed price of the model it picks, with nothing added for the routing.

- Model ID: smart-router
- Type: Text
- Publisher: OceanToken
- Price: Billed at the model it picks: each request costs what that model lists, with nothing added for the routing
- Capabilities: text in, text out
- Endpoint: /v1/chat/completions, /v1/responses
- API shape: OpenAI-compatible
- In the catalog since: 2026-08-10
- Page: https://docs.oceantoken.ai/models/smart-router

## Endpoints

- POST `/v1/chat/completions` (openai shape): Chat completions. Send a conversation to a language model and get the next message back. Streams with `stream: true`.
- POST `/v1/responses` (openai shape): Responses. The stateful successor to chat completions, with built-in tools and multi-turn state.
- POST `/v1/messages` (anthropic shape): Messages. Anthropic-style messages for Claude models. Use the Anthropic SDK unchanged.
- POST `/v1/images/generations` (openai shape): Image generation. Generate images from a text prompt.
- POST `/v1/images/edits` (openai shape): Image edits. Edit an image with a prompt and an optional mask.
- POST `/v1/videos` (openai shape): Create a video job. Start a video generation job. Videos take minutes; poll the job, then fetch the finished file. Send an `Idempotency-Key` so a retry cannot start a second job.
- GET `/v1/videos` (openai shape): List video jobs. Your recent video jobs and their states.
- GET `/v1/videos/{video_id}` (openai shape): Video status. The state of a video job and, once finished, where to download it.
- GET `/v1/videos/{video_id}/content` (openai shape): Video content. Download the finished video file.
- POST `/v1/embeddings` (openai shape): Embeddings. Turn text into vectors for search and retrieval.
- POST `/v1/audio/speech` (openai shape): Text to speech. Turn text into spoken audio.
- POST `/v1/audio/transcriptions` (openai shape): Transcription. Turn an audio file into text.
- POST `/v1/rerank` (cohere shape): Rerank. Order a list of documents by relevance to a query.
- GET `/v1/models` (openai shape): List models. Every model your key can call, in OpenAI's list format.
- GET `/v1/usage/{request_id}` (oceantoken shape): Request cost. What one request cost and the tokens it used, looked up by the `id` of its response. For streamed responses, whose cost cannot travel in a header.