Mistral: Mistral Small 4 (batch)
Analysis Summary
Mistral Small 4 is a multimodal model supporting text and images, with a 262,144-token context window, tool use, and function calling. It has the interface features needed for document review, visual content handling, structured outputs, and lightweight agent workflows. However, the supplied record includes no benchmark data for reasoning, coding, or instruction following.
Pricing is low at $0.15 per million input tokens and $0.60 per million output tokens, making it suitable for high-volume testing and routine automation. It could serve as a value-tier model for extraction, classification, and content transformation. Keep a stronger model in the loop for complex reasoning, autonomous coding, and client-facing work where consistency has not yet been demonstrated.
Assessed September 7, 2026
Editorial notes
Mistral Small 4 combines vision, a 262K context window, tool use, and function calling with low pricing. The supplied record has no benchmark data, so it is best positioned as a cost-conscious candidate for routine workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
DFO Verdict
Mistral Small 4 combines vision, a 262K context window, tool use, and function calling with low pricing. The supplied record has no benchmark data, so it is best positioned as a cost-conscious candidate for routine workflows.
How Mistral: Mistral Small 4 (batch) compares
Its 262K-token context window is larger than 71% of the models we list. At $0.15 per million input tokens it is cheaper than 61% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Strongest on value. The pulled-in technical corner is the trade-off, and if the shape matters more than the price, this is your model.
Compare shapes side-by-side →Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.15 | $0.000150 |
| Output | $0.60 | $0.000600 |
What would Mistral: Mistral Small 4 (batch) cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 756 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Mistral: Mistral Small 4 (batch) for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout Mistral: Mistral Small 4 (batch)
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from..
Frequently asked questions about Mistral: Mistral Small 4 (batch)
How much does Mistral: Mistral Small 4 (batch) cost?
Mistral: Mistral Small 4 (batch) costs $0.15 per million input tokens and $0.60 per million output tokens.
What is the context window of Mistral: Mistral Small 4 (batch)?
Mistral: Mistral Small 4 (batch) has a context window of 262,144 tokens (262K).
What can Mistral: Mistral Small 4 (batch) do?
Mistral: Mistral Small 4 (batch) supports image/vision input, tool use, and function calling.
Who created Mistral: Mistral Small 4 (batch)?
Mistral: Mistral Small 4 (batch) is developed by Mistral and was released on March 16, 2026.