Get started
Supported models
SambaNova Cloud currently supports the following models for all developer and enterprise accounts:
Production models
Production models are intended for use in production environments and meet our high standards for speed and quality.| Developer | Model ID | Context length | View on Hugging Face |
|---|---|---|---|
| DeepSeek | |||
DeepSeek-R1 | 32k tokens | Model card | |
DeepSeek-V3-0324 | 32k tokens | Model card | |
DeepSeek-R1-Distill-Llama-70B | 128k tokens | Model card | |
| Meta | |||
Meta-Llama-3.3-70B-Instruct | 128k tokens | Model card | |
Meta-Llama-3.1-8B-Instruct | 16k tokens | 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 | Max file size1 | View on Hugging Face |
|---|---|---|---|---|
| Meta | ||||
Llama-4-Maverick-17B-128E-Instruct | 128k tokens | N/A | Model card | |
| OpenAI | ||||
Whisper-Large-v3 | N/A | 25MB | Model card | |
| Qwen | ||||
Qwen3-32B | 8k tokens | N/A | Model card | |
| Tokyotech-llm | ||||
Llama-3.3-Swallow-70B-Instruct-v0.4 | 16k tokens | N/A | Model card | |
| Other | ||||
E5-Mistral-7B-Instruct | 4k tokens | N/A | Model card |
1Audio models only.
On Request Models
On Request Models include both deprecated cloud models and select models not available in the standard SambaCloud 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 our sales team.- See the complete list of On Request models.
- See more about our deprecation process.