Resources
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.
Below is the complete list of models available through SambaNova’s On Request tier:
For more details on our deprecation process, see the Model deprecations page.
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.