Mistral Small 4 pricing
$$ Standard$0.15/M input · $0.60/M output. List prices from provider data; in idapt, chat is metered per token with transparent, usage-based pricing at the prices shown in the app.
Full rate table
| Rate | Price | Unit |
|---|---|---|
| Input | 0.15 | /M tokens |
| Output | 0.6 | /M tokens |
| Cache read | 0.015 | /M tokens |
What typical work costs
| Workload | Tokens | List price |
|---|---|---|
| Quick question | 1K tokens in, 500 out | $0.0004 |
| Long-document summary | 60K tokens in, 2K out | $0.01 |
| Agent working session | 400K tokens in, 40K out across a day | $0.08 |
Price your own workload
- Per call
- $0.0004
- Per month
- $0.04
Compare up to four models at once in the cost calculator.
Frequently asked
What does Mistral Small 4 cost per 1M tokens?
Mistral Small 4 lists at $0.15 per 1M input tokens and $0.60 per 1M output tokens.
Does Mistral Small 4 discount cached input tokens?
Yes. Cached input tokens are billed at $0.01 per 1M, versus $0.15 for fresh input. Prompts that repeat a long prefix (a system prompt, attached files) benefit the most.
What does a typical chat message with Mistral Small 4 cost?
A message with about 1,000 input tokens and a 500-token reply costs roughly $0.0004 at list price. Long documents and long replies scale that linearly with token counts.
Is Mistral Small 4 cheaper than Mistral Small 3.1?
Mistral Small 4 has the lower blended price at a 3:1 input:output mix. Mistral Small 4: $0.15 in / $0.60 out per 1M. Mistral Small 3.1: $0.35 in / $0.55 out per 1M.
How does idapt bill Mistral Small 4?
Chat with Mistral Small 4 in idapt is metered per token with transparent, usage-based pricing at the prices shown in the app. Subscriptions include a weekly usage allowance before any balance is touched.
Part of the Mistral Small 4 model page · cheapest models board · price changes