SambaNova pricing overview
TokenWatch tracks 8 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: gpt-oss-120b at $0.220 per million input tokens and $0.590 per million output tokens. 1 of 8 text models publish a cache-read price; 6 carry a zero-data-retention tag.
SambaNova text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| minimax | sambanova | MiniMax-M3.1-Flash | $0.300 | $1.20 | $0.030 | $0.043 |
| openai | sambanova | gpt-oss-120b | $0.220 | $0.590 | — | $0.222 |
| sambanova | gemma-4-31B-it | $0.380 | $1.15 | — | $0.384 | |
| meta | sambanova | Meta: Llama 3.3 70B Instruct | $0.450 | $0.900 | — | $0.452 |
| meta | sambanova | Meta-Llama-3.3-70B-Instruct | $0.600 | $1.20 | — | $0.603 |
| deepseek | sambanova | DeepSeek: DeepSeek V3.1 | $0.650 | $1.50 | — | $0.654 |
| deepseek | sambanova | DeepSeek-V3.1 | $3.00 | $4.50 | — | $3.01 |
| deepseek | sambanova | DeepSeek-V3.2 | $3.00 | $4.50 | — | $3.01 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.