# Titan Embed Text V2 (`amazon/titan-embed-text-v2`): API > amazon/titan-embed-text-v2 is a text embedding model from Amazon you can call on the OceanToken API, with a 8K-token context window. Endpoint: `POST https://api.oceantoken.ai/v1/embeddings`. Auth: `Authorization: Bearer $OCEANTOKEN_API_KEY`. OpenAI-compatible; the OpenAI SDKs work with base URL https://api.oceantoken.ai/v1. ## Request parameters - `model` (string; required): This model's ID. - `input` (string or array; required): A string, or a list of strings to embed in one request. - `encoding_format` (string; float, base64; default "float"): How the vectors come back. ## Example: Basic ```bash curl https://api.oceantoken.ai/v1/embeddings \ -H "Authorization: Bearer $OCEANTOKEN_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "amazon/titan-embed-text-v2", "input": "The quick brown fox" }' ``` ```python import os from openai import OpenAI client = OpenAI(base_url="https://api.oceantoken.ai/v1", api_key=os.environ["OCEANTOKEN_API_KEY"]) result = client.embeddings.create( model="amazon/titan-embed-text-v2", input="The quick brown fox", ) print(len(result.data[0].embedding)) ``` ## Response - `data[].embedding` (array): The vector. - `usage.prompt_tokens` (integer): Input tokens. ```json { "object": "list", "data": [ { "object": "embedding", "index": 0, "embedding": [ 0.0123, -0.0456 ] } ], "usage": { "prompt_tokens": 5, "total_tokens": 5 } } ``` ## More - Model page: https://docs.oceantoken.ai/models/amazon/titan-embed-text-v2 - This spec as JSON (with a JSON Schema of the request): https://docs.oceantoken.ai/models/amazon/titan-embed-text-v2/spec.json - Guide: https://docs.oceantoken.ai/guides/embeddings-rerank - All models: https://docs.oceantoken.ai/llms.txt