Serverless inference cloud for open-weight LLMs, image, video, TTS, transcription, embedding, and reranker models with an OpenAI-compatible API.
| Model |
|---|
DeepSeek-R1-Distill-Llama-70BOSSdeepseek-ai/DeepSeek-R1-Distill-Llama-70B |
llama-nemotron-embed-vl-1b-v2nvidia/llama-nemotron-embed-vl-1b-v2 |
llama-nemotron-rerank-vl-1b-v2nvidia/llama-nemotron-rerank-vl-1b-v2 |