SambaNova
Discover SambaNova - the complete AI platform delivering the fastest AI inference, fine-tuning, and scalable solutions for agentic AI easily integrated into existing data center infrastructures. Inference platform · OpenAI-compatible API · Enterprise · Fast Inference · Open Weight · Rdu
Intelligence vs Price
Best value among SambaNova models on this chart: MiniMax M2.7 · QwQ 32B · Qwen3 32B (and 3 more on the dashed frontier). Prices use each model's lowest available SambaNova price across regions. Hover any dot for full pricing, or click a creator in the legend to isolate.
SambaNova models
17 models in Global, 17 with pricing| Select | Model | Creator | Input Price, $ | Output Price, $ | Context | Max Output | Inference Providers | Intelligence | Coding |
|---|---|---|---|---|---|---|---|---|---|
| MiniMax M2.7 | 0.6 | 2.40 | 1.0M | 131K | #1 | #1 | |||
| DeepSeek V3.2 | 3.00 | 4.50 | 164K | 147K | #2 | #2 | |||
| DeepSeek V3.1 | 3.00 | 4.50 | 164K | 128K | #3 | N/A | |||
| DeepSeek R1 | 5.00 | 7.00 | 164K | 66K | #4 | #3 | |||
| DeepSeek V3 324 | 3.00 | 4.50 | 164K | 66K | #5 | #4 | |||
| QwQ 32B | 0.5 | 1.00 | 131K | 16K | #6 | N/A | |||
| Qwen3 32B | 0.4 | 0.8 | 131K | 41K | #7 | #5 | |||
| DeepSeek R1 Distill Llama 70B | 0.7 | 1.40 | 131K | 8K | #8 | N/A | |||
| Llama 3.3 70B Instruct | 0.6 | 1.20 | 131K | 120K | #9 | #6 | |||
| Llama 3.1 405B Instruct | 5.00 | 10.00 | 131K | 16K | #10 | N/A | |||
| Llama 3.1 8B Instruct | 0.1 | 0.2 | 200K | 128K | #11 | #7 | |||
| Llama 3.2 3B Instruct | 0.08 | 0.16 | 131K | 118K | #12 | N/A | |||
| Llama 3.2 1B Instruct | 0.04 | 0.08 | 131K | 54K | #13 | N/A | |||
| Gemma 4 31B IT | 0.38 | 1.15 | 262K | 131K | N/A | N/A | |||
| Llama 4 17B Maverick Instruct | 0.63 | 1.80 | 1.0M | 16K | N/A | N/A | |||
| Llama 4 17B Scout Instruct | 0.4 | 0.7 | 10.0M | 16K | N/A | N/A | |||
| LlamaGuard 3 8B | 0.3 | 0.3 | 131K | 16K | N/A | N/A |