NVIDIA models on OceanToken
15 NVIDIA models (embeddings, rerank, text, transcription) callable through the OceanToken API with one key and one prepaid balance, each with its price per unit, context window and capabilities.
| Model | Type | Context | Price |
|---|---|---|---|
Llama Nemotron Embed VL 1B V2 (Free)nvidia/llama-nemotron-embed-vl-1b-v2:free | Embeddings | 131,072 | Free, rate-limited |
Llama Nemotron Rerank VL 1B V2 (Free)nvidia/llama-nemotron-rerank-vl-1b-v2:free | Rerank | Free, rate-limited | |
Nemotron 3 Embed 1B (Free)nvidia/nemotron-3-embed-1b:free | Embeddings | 32,768 | Free, rate-limited |
Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | Text | 262,144 | $0.06 per 1M tokens · $0.24 per 1M tokens |
Nemotron 3 Nano Omni 30B A3B Reasoning (Free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Text | 256,000 | Free, rate-limited |
Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b | Text | 262,144 | $0.085 per 1M tokens · $0.40 per 1M tokens |
Nemotron 3 Super 120B A12B (Free)nvidia/nemotron-3-super-120b-a12b:free | Text | 262,144 | Free, rate-limited |
Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b | Text | 262,144 | $0.60 per 1M tokens · $2.40 per 1M tokens |
Nemotron 3 Ultra 550B A55B (Free)nvidia/nemotron-3-ultra-550b-a55b:free | Text | 1,000,000 | Free, rate-limited |
Nemotron 3.5 ASR Streaming Multilingual 0.6bnvidia/nemotron-3.5-asr-streaming-multilingual-0.6b | Transcription | $0.0002 per minute of audio | |
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety | Text | 131,072 | $0.20 per 1M tokens · $0.20 per 1M tokens |
Nemotron 3.5 Content Safety (Free)nvidia/nemotron-3.5-content-safety:free | Text | 128,000 | Free, rate-limited |
Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | Text | 262,144 | $0.06 per 1M tokens · $0.16 per 1M tokens |
Nemotron 3.5 Lightning (Free)nvidia/nemotron-3.5-lightning:free | Text | 1,000,000 | Free, rate-limited |
Parakeet Tdt 0.6b V3nvidia/parakeet-tdt-0.6b-v3 | Transcription | $0.0015 per minute of audio |
Every model above is called with the same key, the same base URL and the same prepaid balance; see your first request and the full model catalog.