Mistral: Devstral Small 1.1
Analysis Summary
Devstral Small 1.1 is a low-cost Mistral model aimed at software and file-based workflows. It provides a 131K context window, file input, tool use, and function calling, while its coding benchmark is useful for routine implementation and code transformation. The input and output prices are particularly attractive for volume usage.
Agencies can use it for boilerplate generation, repository navigation, issue triage, and structured developer assistance. Its limited general reasoning, modest instruction-following result, and low long-context score make it a poor choice for complex architecture, nuanced client copy, or unsupervised agents. Human review remains important when changes affect production systems.
Adopt Devstral Small 1.1 as an economical engineering utility. Pair it with a stronger reasoning model for planning, validation, and high-consequence code.
Assessed September 7, 2026
Editorial notes
Devstral Small 1.1 is an inexpensive coding model with a 131K context window, file input, tool use, and function calling. It suits routine engineering automation, but its reasoning and long-context results limit high-stakes autonomous work.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
DFO Verdict
Devstral Small 1.1 is an inexpensive coding model with a 131K context window, file input, tool use, and function calling. It suits routine engineering automation, but its reasoning and long-context results limit high-stakes autonomous work.
Benchmark scores
Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.
3.6 Intelligence Index·29.3 Math Index
How Mistral: Devstral Small 1.1 compares
Mistral: Devstral Small 1.1 ranks #310 of 435 AI models we track for overall intelligence. Its 131K-token context window is larger than 48% of the models we list. At $0.10 per million input tokens it is cheaper than 70% 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 | $0.10 | $0.000100 |
| Output | $0.30 | $0.000300 |
What would Mistral: Devstral Small 1.1 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: Devstral Small 1.1 for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout Mistral: Devstral Small 1.1
Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and..
Frequently asked questions about Mistral: Devstral Small 1.1
How much does Mistral: Devstral Small 1.1 cost?
Mistral: Devstral Small 1.1 costs $0.10 per million input tokens and $0.30 per million output tokens.
What is the context window of Mistral: Devstral Small 1.1?
Mistral: Devstral Small 1.1 has a context window of 131,072 tokens (131K).
What can Mistral: Devstral Small 1.1 do?
Mistral: Devstral Small 1.1 supports tool use and function calling.
Who created Mistral: Devstral Small 1.1?
Mistral: Devstral Small 1.1 is developed by Mistral and was released on July 10, 2025.