SambaNova Cloud API provides access to DeepSeek models, the Llama 3.3, 3.2, and 3.1 family of models, as well as the Qwen 2.5 family, all at full precision. SambaNova provides access to all models for all tiers.

​
Model details

A structured comparison of various models across the Qwen and Llama families is provided below. It describes key specifications such as model name, ID, developer, context length, and provides links to their respective model cards.

​
Preview models

Preview models in SambaNova Cloud are offered as early access models primarily for trial purposes. During the Preview phase, these models are available exclusively in the playground.

For API access and higher rate limits for DeepSeek-R1, please complete this form to join the waitlist.

DeveloperModel IDContext LengthModel card
DeepSeek
DeepSeek-R14k tokensView on Hugging Face

​
Production models

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

DeveloperModel IDContext lengthModel card
DeepSeek
DeepSeek-R1-Distill-Llama-70B16k tokensView on Hugging Face
Ai2
Llama-3.1-Tulu-3-405B16k tokensView on Hugging Face
Meta
Meta-Llama-3.3-70B-Instruct16k tokensView on Hugging Face
Meta-Llama-3.2-3B-Instruct8k tokensView on Hugging Face
Meta-Llama-3.2-1B-Instruct16k tokensView on Hugging Face
Meta-Llama-3.1-405B-Instruct16k tokensView on Hugging Face
Meta-Llama-3.1-70B-Instruct128k tokensView on Hugging Face
Meta-Llama-3.1-8B-Instruct16k tokensView on Hugging Face
Meta-Llama-Guard-3-8B8k tokensView on Hugging Face
Llama-3.2-90B-Vision-Instruct4k tokensView on Hugging Face
Llama-3.2-11B-Vision-Instruct4k tokensView on Hugging Face
Qwen
Qwen2.5-72B-Instruct16k tokensView on Hugging Face
Qwen2.5-Coder-32B-Instruct16k tokensView on Hugging Face
QwQ-32B-Preview16k tokensView on Hugging Face
Qwen2-Audio-7B-Instruct-View on Hugging Face
QuickstartOpenAI compatibility