SambaCloud Supported Models - SambaNova Documentation

SambaCloud currently supports the following models for all developer accounts. For definitions of the Production and Preview designations, see the Glossary.

Production models

Production models are intended for use in production environments and meet SambaNova’s high standards for speed and quality.

Developer	Model ID	Context length	Supported modalities	View on Hugging Face
DeepSeek	`DeepSeek-V3.1`	128k tokens	Text	Model card
Meta	`Meta-Llama-3.3-70B-Instruct`	128k tokens	Text	Model card
OpenAI	`gpt-oss-120b`	128k tokens	Text	Model card

Preview models

Preview models are intended for evaluation purposes and developer experimentation only, and should not be used in production environments. These models have limited capacity and may be removed at short notice.

Developer	Model ID	Context length	Supported modalities	View on Hugging Face
MiniMax	`MiniMax-M3`	1M tokens	Text	Model card
DeepSeek	`DeepSeek-V3.2`	32k tokens	Text	Model card
Google	`gemma-4-31B-it`	128k tokens	Text, Image, Video	Model card

MiniMax-M3 runs as a text-only deployment on SambaCloud. Image and video input are not currently accepted; requests with media content return an error.

gemma-4-31B-it supports text, image, and video input. Audio input is not supported for this model.