Codestral (latest)
Codestral (latest)
📌 Model Overview
Mistral code model for completions, refactors, and developer IDE workflows
Codestral (latest) is a Open Weights model developed by Mistral AI, released on 2024-05-29. It is designed primarily for Chat Reasoning workloads. Featuring a 256K tokens context window and Undisclosed parameter count, it offers robust performance for enterprise integration, developers, and researchers.
✨ Key Features & Capabilities
| Feature | Description |
|---|---|
| Context Window | 256K tokens capacity for extended prompts and multi-turn workflows |
| Primary Task | Optimized for Chat Reasoning |
| Deployment | self-hostable, api-only |
| Modality | text |
| Max Output | Max Output: 4K tokens |
| Tool / function calling support | Tool / function calling support |
⚙️ Technical Specifications
| Specification | Details |
|---|---|
| Developer / Lab | Mistral AI |
| Release Date | 2024-05-29 |
| Model Type | Open Weights |
| Parameters | Undisclosed |
| Context Window | 256K tokens |
| License | Apache-2.0 |
| Model Family | codestral |
📊 Benchmarks & Performance
| Benchmark | Score | Source |
|---|---|---|
| Aider Polyglot | 11.1% | Independent Eval |
💰 Pricing
| Tier / Unit | Rate (USD) |
|---|---|
| 1M input tokens | $0.3 |
| 1M output tokens | $0.9 |
🔗 Resources & Links
| Resource | Link |
|---|---|
| Hugging Face | https://huggingface.co/mistralai/Codestral-22B-v0.1 |
📜 License & Usage
This model is governed by the Apache-2.0 license. Please check official developer guidelines before commercial deployment.
Key Features
Max Output: 4K tokens
Tool / function calling support
You might also want to compare
Verified Sources
Tags
Model Specs
Parameters
Undisclosed
Context Window
256K tokens
License
Apache-2.0
Deployment
Pricing
- 1M input tokens$0.3
- 1M output tokens$0.9
as of 2026-07-26
Resources & Links
Lineage
Model Family
Part of the codestral family
Only release in this line currently tracked.
Curator Notes
Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.
Compare Specs
Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.
Compare Model