Mistral: Mistral Small 3.1 24B (free)
Analysis Summary
Mistral Small 3.1 24B (free) is a text-and-image model with a 128K context window, tool use, and function calling. Its measured coding capability is stronger than its general reasoning and agentic results, suggesting a practical assistant for defined technical tasks rather than a leading autonomous agent. The record lists no token price for this free version.
For client workflows, it is a candidate for coding assistance, visual input tasks, structured tool calls, and content drafts that receive review. The combination of modality and integrations makes it more deployable than a text-only model without tools, but weak agentic and long-context results limit the case for unsupervised multi-step work or lengthy document synthesis. Test output quality against the specific task before expanding usage.
Free access makes it appealing for pilots and routine traffic where its capability is sufficient. Retain human checks for code changes and customer-facing material, and escalate high-stakes reasoning to a stronger model.
Assessed September 23, 2026
Editorial notes
Free Mistral Small 3.1 24B combines vision, tool and function calling, a 128K context, and useful coding capability; its reasoning and agentic results fall short of top-tier models.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
Free Mistral Small 3.1 24B combines vision, tool and function calling, a 128K context, and useful coding capability; its reasoning and agentic results fall short of top-tier models.
Benchmarks
Artificial Analysis data refreshed Oct 15, 2026. Arena ratings from the Oct 13, 2026 text leaderboard, with style control.
Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.
How Mistral: Mistral Small 3.1 24B (free) compares
Mistral: Mistral Small 3.1 24B (free) ranks #198 of 439 AI models we track for overall intelligence, #129 of 198 for coding, #118 of 181 for agentic tasks. Its 128K-token context window is larger than 37% of the models we list. Mistral: Mistral Small 3.1 24B (free) is currently free to use via OpenRouter.
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.
About Mistral: Mistral Small 3.1 24B (free)
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments. The updated version is Mistral Small 3.2
Frequently asked questions about Mistral: Mistral Small 3.1 24B (free)
How much does Mistral: Mistral Small 3.1 24B (free) cost?
Mistral: Mistral Small 3.1 24B (free) is currently available for free via OpenRouter.
What is the context window of Mistral: Mistral Small 3.1 24B (free)?
Mistral: Mistral Small 3.1 24B (free) has a context window of 128,000 tokens (128K).
Is Mistral: Mistral Small 3.1 24B (free) good for coding?
On our coding benchmark index, Mistral: Mistral Small 3.1 24B (free) ranks #129 of 198 models, placing it in the broader range of the field for code generation and debugging.
What can Mistral: Mistral Small 3.1 24B (free) do?
Mistral: Mistral Small 3.1 24B (free) supports image/vision input, tool use, and function calling.
Who created Mistral: Mistral Small 3.1 24B (free)?
Mistral: Mistral Small 3.1 24B (free) is developed by Mistral and was released on March 17, 2025.