Mistral: Devstral 2 2512
Analysis Summary
Devstral 2 2512 from Mistral is positioned as a coding-oriented model, with an intelligence index of 15.5 and a coding index of 23.7. Agentic performance at 21.9 is low, and math at 36.7 is moderate. Tool use and function calling are supported, and the 262K context window is useful for larger codebases. MMLU Pro at 0.762 shows reasonable general knowledge.
For businesses, Devstral 2 suits routine code generation, code review assistance, and lightweight tool-use workflows where cost efficiency is a priority. The coding index is not competitive with the top coding models, but it is adequate for standard development support tasks. Complex agentic orchestration or multi-step reasoning is beyond its reliable range.
At $0.40 input and $2.00 output, pricing is reasonable for a Mistral model with tool use. Teams needing a low-cost coding assistant with a large context window and Mistral's enterprise backing will find it a practical option for routine tasks, with the understanding that frontier coding capability requires a higher-tier model.
Assessed June 17, 2026
Editorial notes
Mistral's Devstral 2 2512 is a coding-focused model with tool use and a 262K context window at low cost, but reasoning and agentic scores are limited, making it best suited to routine code generation rather than complex engineering workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Mistral: Devstral 2 2512 compares
Mistral: Devstral 2 2512 ranks #169 of 380 AI models we track for overall intelligence, #171 of 292 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.40 per million input tokens it is cheaper than 39% of comparable models.
About Mistral: Devstral 2 2512
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Mistral: Devstral 2 2512 stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
mistralai/devstral-2512
|
| Provider | mistralai |
| Release Date | December 9, 2025 |
| Context Length | 262,144 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.40 | $0.000400 |
| Output | $2.00 | $0.002000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Mistral: Devstral 2 2512
How much does Mistral: Devstral 2 2512 cost?
Mistral: Devstral 2 2512 costs $0.40 per million input tokens and $2.00 per million output tokens.
What is the context window of Mistral: Devstral 2 2512?
Mistral: Devstral 2 2512 has a context window of 262,144 tokens (262K).
What can Mistral: Devstral 2 2512 do?
Mistral: Devstral 2 2512 supports tool use and function calling.
Who created Mistral: Devstral 2 2512?
Mistral: Devstral 2 2512 is developed by Mistral and was released on December 9, 2025.
