Mistral Small 4 API Pricing
Mistral Small 4 by Mistral costs $0.15 per million input tokens and $0.60 per million output tokens.
Price verified from Mistral's pricing page.
Rates and limits
- Input / 1M
- $0.15
- Output / 1M
- $0.60
- Cached input / 1M
- Not listed
- Batch discount
- None
- Context window
- 256K tokens
- Released
- March 2026
Pricing note: Apache 2.0 open weights. Mistral advertises Batch at half price and cached input at -90% as account-wide options; per-model rates are not listed, so they are not applied here.
What Mistral Small 4 costs per month
Token volume split 3:1 between input and output, with no prompt caching.
| Tokens per month | Input / output | Standard |
|---|---|---|
| 1M | 750K / 250K | $0.26 |
| 10M | 7.5M / 2.5M | $2.63 |
| 100M | 75M / 25M | $26.25 |
Where to run Mistral Small 4
Prices above are Mistral's direct rates. Cloud platforms can charge differently; the cloud platform view compares them.
- Mistral La PlateformeDirect API
- OpenRouterCloud / platform
Mistral Small 4 pricing FAQ
How much does Mistral Small 4 cost per million tokens?
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens, as listed on Mistral's pricing page on September 30, 2026.
How much does Mistral Small 4 cost for 10 million tokens a month?
About $2.63 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching.
What is the context window of Mistral Small 4?
Mistral Small 4 accepts up to 256,000 tokens of context.
Does Mistral Small 4 support prompt caching?
No cached-input price is listed for Mistral Small 4, so repeated prompt prefixes are billed at the standard input rate.
Is there a batch discount for Mistral Small 4?
No batch API price is listed for Mistral Small 4.
Where can I use the Mistral Small 4 API?
Mistral Small 4 is available through Mistral La Plateforme and OpenRouter.
Compare with other models
More from Mistral
Prices shown as input / output per million tokens. All model prices · Side-by-side comparison