# SambaNova AI

SambaNova AI is a full-stack AI systems company that builds advanced hardware and software solutions for generative AI. Their cloud platform provides access to leading open-source models including DeepSeek (R1, V3, V3.1, V3.2), Meta Llama (3.1, 3.3, 4-Maverick), Qwen3 (32B, 235B), and other specialized models. SambaNova offers an OpenAI-compatible API with competitive pricing, featuring models with context windows up to 131K tokens. The company is known for their DataScale systems and SN40L AI chip designed specifically for large language model training and inference.

## Provider Information

- **Website**: <https://sambanova.ai/>
- **Available Models**: 13

## Models

| Name | Original Name | $ Input Price (per 1M) | $ Output Price (per 1M) | Free | Link |
|------|---------------|---------------------|----------------------|------|------|
| DeepSeek-R1-0528 | DeepSeek-R1-0528 | 5.00 | 7.00 |  |  |
| DeepSeek-R1-Distill-Llama-70B | DeepSeek-R1-Distill-Llama-70B | 0.70 | 1.40 |  |  |
| DeepSeek-V3-0324 | DeepSeek-V3-0324 | 3.00 | 4.50 |  |  |
| DeepSeek-V3.1 | DeepSeek-V3.1 | 3.00 | 4.50 |  |  |
| DeepSeek-V3.1-Terminus | DeepSeek-V3.1-Terminus | 3.00 | 4.50 |  |  |
| DeepSeek-V3.2 | DeepSeek-V3.2 | 3.00 | 4.50 |  |  |
| Llama-4-Maverick-17B-128E-Instruct | Llama-4-Maverick-17B-128E-Instruct | 0.63 | 1.80 |  |  |
| Meta-Llama-3.1-8B-Instruct | Meta-Llama-3.1-8B-Instruct | 0.10 | 0.20 |  |  |
| Meta-Llama-3.3-70B-Instruct | Meta-Llama-3.3-70B-Instruct | 0.60 | 1.20 |  |  |
| Qwen3-32B | Qwen3-32B | 0.40 | 0.80 |  |  |
| Whisper-Large-v3 | Whisper-Large-v3 | 0.00 | 0.00 | Yes |  |
| gpt-oss-120b | gpt-oss-120b | 0.22 | 0.59 |  |  |
| MiniMax-M2.5 | MiniMax-M2.5 | 0.30 | 1.20 |  |  |

---

[← Back to all providers](/llm.txt)