SambaNova pricing & review
RDU-based inference cloud serving large open models (405B-class) at high speed with per-token pricing.
Where SambaNova wins
- Fast large-model serving
- Full-precision open models
SambaNova model pricing
List prices refreshed 2026-10-08 ยท cheapest 25 shown| Model | Input $/1M | Output $/1M | Market floor in |
|---|---|---|---|
| GPT-OSS 120B | $0.220 | $0.590 | $0.030at W&B Inference |
| Gemma 4 31B | $0.380 | $1.15 | $0.090at OpenRouter |
| Llama 3.3 70B | $0.600 | $1.20 | $0.120at Hyperbolic |
| MiniMax M2.7 | $0.600 | $2.40 | $0.210at OpenRouter |
| Llama 4 Maverick | $0.630 | $1.80 | $0.050at Lambda |
| DeepSeek V3.2 | $3.00 | $4.50 | $0.260at DeepInfra |
| DeepSeek-V3.1 | $3.00 | $4.50 | $0.250at DeepInfra |
| DeepSeek R1 | $5.00 | $7.00 | $0.200at Lambda |