Mistral Small
At a glance
- Price per 1M tokens (input)
- $0.10
- Price per 1M tokens (output)
- $0.30
- Context
- 32,000 tokens
- Free access
- yes (see below)
Refreshed daily; data verified November 16, 2026. Published August 12, 2026, last price change September 18, 2026.
Mistral Small is a general-purpose language model from Mistral AI, a vendor that releases models under open weights and prioritizes efficient inference. It suits teams that need a balance between capability and operational cost for tasks such as document summarization, customer support automation, and structured data extraction. The model supports tool calling, meaning it can connect to external functions or APIs to perform actions rather than only generate text. It also provides step-by-step reasoning, which helps it work through multi-part problems by showing intermediate logic before delivering a final answer.
Specifications & pricing
| Input (per 1M tokens) | $0.10 |
|---|---|
| Output (per 1M tokens) | $0.30 |
| Cache read (per 1M tokens) | $0.01 |
| Context window | 32,000 tokens |
| Max output | 8,191 tokens |
| Capabilities | tool calling, reasoning |
LiteLLM community dataset (MIT), verified November 16, 2026. Official Mistral AI pricing.
What Mistral Small would cost on your workload — run it through the cost calculator →
Price history
| Date | Input / 1M | Output / 1M |
|---|---|---|
| August 9, 2026 (first record) | $0.10 | $0.30 |
| September 18, 2026 | $0.10 | $0.30 |
Where to try Mistral Small for free
- Mistral AI offers a free chat — Le Chat (free plan). A vendor's free chat may run a different model from the same family — the exact model is not guaranteed.
Frequently asked questions
What is this model good for?+
Mistral Small is suited for business tasks that require both language understanding and action, such as routing support tickets, extracting fields from invoices, and powering chat agents that call internal APIs. Its reasoning capability makes it useful for multi-step workflows where the model must evaluate options before responding.
How do I get started?+
Access the model through Mistral AI's platform or a compatible inference provider, then send prompts using the chat completion interface. To use tool calling, define your available functions in the request and let the model return structured calls that your application can execute.
How does it differ from other Mistral models?+
Mistral Small sits between the smaller, faster models and the larger, more capable models in the line. It offers stronger reasoning and broader knowledge than lightweight variants while remaining less resource-intensive than the flagship models, making it a practical middle ground for production workloads.
What are its limitations?+
Like other language models, it can produce incorrect or unsupported information and may struggle with highly specialized domains without additional context or fine-tuning. Tool calling depends on clear function definitions and reliable external APIs, and reasoning chains can still contain logical errors that require human review.
Compare with others

Org chart: how to move your company onto AI
A practical map: which company roles and processes AI agents can take over, where to start, and in what order to roll it out.