SambaNova Cloud API pricing
Model AggregatorSambaNova Cloud runs open models (DeepSeek, Llama, Qwen) on custom RDU hardware for record-fast token throughput, billed per token.
Compare the published API prices listed for SambaNova Cloud. Open a model for its available pricing tiers, source and conditions, or use the cost planner to estimate your own workload.
SambaNova Cloud API cost examples
1,000 requests, each using 1,000 input tokens and 200 billed text output tokens: 1M input and 200K output tokens in total.
| Model | Input / 1M tokens | Output / 1M tokens | Estimated cost | Pricing conditions |
|---|---|---|---|---|
| gpt-oss-120bSambaNova Cloud | $0.22 | $0.59 | $0.338 | Region not specifiedView official pricing |
| gemma-4-31B-itSambaNova Cloud | $0.38 | $1.15 | $0.61 | Region not specifiedView official pricing |
| Meta-Llama-3.3-70B-InstructSambaNova Cloud | $0.6 | $1.2 | $0.84 | Region not specifiedView official pricing |
| MiniMax-M2.7SambaNova Cloud | $0.6 | $2.4 | $1.08 | Region not specifiedView official pricing |
| MiniMax-M3SambaNova Cloud | $0.6 | $2.4 | $1.08 | Region not specifiedView official pricing |
| DeepSeek-V3.1SambaNova Cloud | $3 | $4.5 | $3.9 | Region not specifiedView official pricing |
Estimates in USD use standard processing, uncached input and the displayed base input tier. Regional rates, longer prompts, thinking tokens and other billable usage can change the final cost. Models can differ in capabilities.
Calculate costs for your workload →