Codestral 25.01
Mistral's Coding Model
Mistral's January 2025 coding model — 22B parameters, 256K context, 80+ programming languages. Codestral excels at fill-in-the-middle (predicting code in the middle of a function, not just appending). The Codestral Mamba sibling uses Mamba state-space architecture for very long context, and Devstral extends to agentic workflows.
Cost
Free
Open weights — self-host
Context
256K
Up to 256,000 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on
Artificial Analysis. Cost buckets are fixed dollar
thresholds keyed off output-token price ($/M out).
Intelligence
- Top 1%≤ 1%
- Top 5%≤ 5%
- Top 10%≤ 10%
- Good≤ 25%
- Medium≤ 50%
- Below avg> 50%
Speed
- Top 1%≥ 345 tok/s
- Top 5%≥ 237 tok/s
- Top 10%≥ 196 tok/s
- Good≥ 146 tok/s
- Medium≥ 90 tok/s
- Slow< 90 tok/s
Cost
- Freeopen weights · self-host
- Low< $1 / M out
- Moderate$1–5 / M out
- High≥ $5 / M out
Why it matters
Codestral helped commoditize the "coding-specialized model" category that previously belonged to GitHub Copilot and DeepSeek- Coder. Now every major lab ships a coding variant.
Core Capabilities
Generative
Produces images, video, audio, or other media.
Coding
Strong real-world software engineering.
Long Documents
Handles entire codebases, books, and multi-doc RAG.
Agent Workflows
Built for tool use and autonomous tasks.
Context Window
256k tokens
≈ 197+ pages
4k Chat 聊天
32k Long docs 长文档
128k Books 整本书
400k Multi-doc 多文档
1M Codebase 整个代码库
10M
256k
Availability
API
Not available
Product / App
Not available
Open Source
Released
Enterprise
—
Pricing Model
Free / self-host
Open weights — pay only for compute.
Self-host Capability / Performance
Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).
Lower 20% Upper 80% This model
Context / memory
Context window size · log-scaled
6.0
9.0
7.0
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this
Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.
What it feels like
- Language model from Mistral AI — see the linked sources below for benchmark and review coverage
- Code-leaning workloads are the typical fit per the published model card
- Tool-use and agent loops are the typical fit per the published model card
Best use cases
- Coding workflows that match the model's published benchmarks
- Agent / tool-use workflows that match the model's published benchmarks
- See the model spec and sources block for benchmarked use cases
Tools to try
Not ideal for
- Tasks far outside the modalities listed in this model's spec
- Workflows where a more recent successor in the same family scores higher