{"data":[{"context_length":4096,"id":"E5-Mistral-7B-Instruct","max_completion_tokens":4096,"object":"model","owned_by":"no-reply@sambanova.ai","pricing":{"completion":"0.00000000","prompt":"0.00000013"},"sn_metadata":{"architecture":"transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias","capabilities":["text","embedding"],"category":[],"github_link":"https://huggingface.co/intfloat/e5-mistral-7b-instruct","hf_link":"https://huggingface.co/intfloat/e5-mistral-7b-instruct","is_external":false,"languages":["English","German","French","Italian","Portuguese","Hindi","Spanish","Thai"],"license":"apache-2.0","name":"E5-Mistral-7B-Instruct","provider":"Mistral","region":"EU","status":"active","vocabulary_size":152064}},{"context_length":1048576,"id":"MiniMax-M3.1-Flash","max_completion_tokens":1048576,"object":"model","owned_by":"no-reply@sambanova.ai","pricing":{"completion":"0.00000120","input_cache_read":"0.00000003","input_cache_write":"0.00000000","prompt":"0.00000030"},"sn_metadata":{"architecture":"minimax-m3-1-flash","capabilities":["text","vision"],"category":[],"github_link":"https://github.com/MiniMax-AI","hf_link":"https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash","is_external":true,"languages":[],"license":"MiniMax Community License","name":"minimaxai/minimax-m3.1-flash","overview":"MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use and cybersecurity. It accepts text, image and video input with up to 1M tokens of context. The model builds on MiniMax-M3 with MiniMax Sparse Attention and quantization-aware training, and supports five reasoning effort levels.","provider":"MiniMax","region":"US","status":"active","text_only":false,"vocabulary_size":200064}},{"context_length":448,"id":"Whisper-Large-v3","max_completion_tokens":448,"object":"model","owned_by":"no-reply@sambanova.ai","pricing":{"completion":"0.00000000","duration_per_hour":"0.100","prompt":"0.00000010"},"sn_metadata":{"architecture":"Whisper","capabilities":["text","audio"],"category":[],"github_link":"https://huggingface.co/openai/whisper-large-v3","hf_link":"https://huggingface.co/openai/whisper-large-v3","is_external":false,"license":"apache-2.0","provider":"OpenAI","region":"EU","status":"active","vocabulary_size":51866}},{"context_length":131072,"id":"gemma-4-31B-it","max_completion_tokens":131072,"object":"model","owned_by":"no-reply@sambanova.ai","pricing":{"completion":"0.00000035","prompt":"0.00000020"},"sn_metadata":{"architecture":"gemma-4-31B-it","capabilities":["text","vision"],"category":[],"github_link":"https://huggingface.co/","hf_link":"https://huggingface.co/","is_external":false,"languages":[],"license":"gemma","name":"google/gemma-4-31B-it","overview":"tbd","provider":"Google","region":"EU","status":"active","text_only":false,"vocabulary_size":262144}},{"context_length":131072,"id":"gpt-oss-120b","max_completion_tokens":131072,"object":"model","owned_by":"no-reply@sambanova.ai","pricing":{"completion":"0.00000059","prompt":"0.00000022"},"sn_metadata":{"architecture":"gpt-oss-120b","capabilities":["text"],"category":[],"github_link":"https://huggingface.co/openai/gpt-oss-120b","hf_link":"https://huggingface.co/openai/gpt-oss-120b","is_external":false,"languages":[],"license":"Apache License 2.0","name":"openai/gpt-oss-120b","overview":"Welcome to the gpt-oss series, OpenAI\u2019s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.","provider":"OpenAI","region":"EU","status":"active","text_only":true,"vocabulary_size":201088}}],"object":"list"}
