Production models

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

DeveloperModel IDContext lengthView on Hugging Face
DeepSeek
DeepSeek-R132k tokensModel card
DeepSeek-V3-032432k tokensModel card
DeepSeek-R1-Distill-Llama-70B128k tokensModel card
Meta
Meta-Llama-3.3-70B-Instruct128k tokensModel card
Meta-Llama-3.1-8B-Instruct16k tokensModel 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.

DeveloperModel IDContext lengthMax file size1View on Hugging Face
Meta
Llama-4-Maverick-17B-128E-Instruct128k tokensN/AModel card
OpenAI
Whisper-Large-v3N/A25MBModel card
Qwen
Qwen3-32B8k tokensN/AModel card
Tokyotech-llm
Llama-3.3-Swallow-70B-Instruct-v0.416k tokensN/AModel card
Other
E5-Mistral-7B-Instruct4k tokensN/AModel card

1Audio models only.

On Request Models

On Request Models include both deprecated cloud models and select models not available in the standard SambaNova Cloud offering. These models can be provisioned on a dedicated node upon request and represent the complete set of models previously supported by SambaNova. To request access, please contact us at [email protected].