Mistral Small 4 API Pricing: Cost Calculator & Real Examples (2026)
Mistral Small 4 charges $0.15 per 1 million input tokens and $0.60 per 1 million output tokens. But per-token prices don't answer the real question: what will your workload cost per month? Below we compute it for three realistic scenarios — or run your own numbers with Mistral Small 4 preselected.
| Meter | Price per 1M tokens |
|---|---|
| Input | $0.15 |
| Cached input | — |
| Output | $0.60 |
What does Mistral Small 4 cost in practice?
| Monthly scenario | Token bill |
|---|---|
| Support chatbot (150k requests, 400 in / 300 out tokens) | $36.00 |
| Document workflow (22k runs, 3,000 in / 400 out tokens) | $15.18 |
| High-volume classifier (1M requests, 300 in / 10 out tokens) | $51.00 |
In the chatbot scenario, output is ~75% of the Mistral Small 4 bill — capping response length (max tokens) is the most direct optimization. Document workflows are input-heavy, so the input rate dominates there.
Prompt caching savings
Mistral Small 4 doesn't publish a per-1M cached-input rate, so budget without that discount (or check the provider's batch options).
Is Mistral Small 4 cheap or expensive?
On the same chatbot workload, Mistral Small 4 is cheaper than 10 of the 11 models we track (position 2 of 12, cheapest to priciest). The nearest cheaper alternative is Gemini 2.5 Flash-Lite ($24.00/month on the same scenario). One step up: GPT-5.6 Luna ($66.00/month). The right decision isn't absolute price but the cheapest model that meets your quality bar — test before overpaying.
FAQ
How much does Mistral Small 4 cost per 1M tokens?
$0.15 per 1M input tokens and $0.60 per 1M output tokens (verified 2026-09-17).
What does a chatbot cost on Mistral Small 4?
A 500-active-user chatbot (10 questions/day, 400 input + 300 output tokens per request) costs ~$36.00/month in tokens on Mistral Small 4. Adjust the assumptions in the calculator.
Our take on this model
Mistral Small is the budget entry of the European stack: cheap classification, extraction and short generation with EU data handling. It pairs naturally with Medium in a two-tier routing setup that keeps everything on one compliant vendor.
Against GPT mini and Flash it competes on compliance more than capability — if that's not your constraint, test all three; if it is, Small is often the only mini-tier on the shortlist.
Prices verified on 2026-09-17 against the provider's official pricing page. Estimates are for planning purposes only — always confirm current pricing with the provider.