Resources
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].
For more details on our deprecation process, see the Model deprecations page.
Below is the complete list of models available through SambaNova’s On Request tier:
While not listed here, current Production and Preview models can also be accessed through a dedicated node upon request.
| Developer | Model ID | Context Length/File Size1 | View on Hugging Face |
|---|---|---|---|
| Meta | |||
Llama-4-Scout-17B-16E-Instruct | 8k tokens | Model card | |
Meta-Llama-3.2-3B-Instruct | 4k tokens | Model card | |
Meta-Llama-3.2-1B-Instruct | 16k tokens | Model card | |
Meta-Llama-3.1-405B-Instruct | 16k tokens | Model card | |
Meta-Llama-Guard-3-8B | 8k tokens | Model card | |
Llama-3.1-Tulu-3-405B | 16k tokens | Model card | |
Llama-3.1-Swallow-70B-Instruct-v0.3 | 16k tokens | Model card | |
Meta-Llama-3.1-70B-Instruct | 128k tokens | Model card | |
Llama-3.2-90B-Vision-Instruct | 4k tokens | Model card | |
Llama-3.2-11B-Vision-Instruct | 4k tokens | Model card | |
| Qwen | |||
Qwen2-Audio-7B-Instruct | 25MB | Model card | |
QwQ-32B | 16k tokens | Model card | |
Qwen2.5-72B-Instruct | 16k tokens | Model card | |
Qwen2.5-Coder-32B-Instruct | 16k tokens | Model card | |
1Audio models only.