# Mistral Codestral — 22B Open-Weight Coding Model

> Codestral is Mistral's coding-specialized model. 22B params, 32K context, 80+ languages including Python, JS, Go, Rust, Bash. Free for non-commercial use.

## Install

Copy the content below into your project:

## Quick Use

1. Local: `ollama pull codestral && ollama run codestral`
2. API: get a key at console.mistral.ai, then `export MISTRAL_API_KEY=...`
3. Plug into Continue / Aider / LiteLLM with the snippets below

---

## Intro

Codestral is Mistral AI's coding-specialized model — 22B parameters, 32K context, trained on 80+ languages from Python and JavaScript to Bash and Fortran. The open-weight Codestral 22B is free for research and non-commercial use; the latest Codestral models are available via Mistral's API and Le Chat for production. Best for: local code completion via Continue / Aider, latency-sensitive code generation. Works with: Ollama, vLLM, llama.cpp, Continue, Aider, LiteLLM. Setup time: 5 minutes (Ollama pull or API key).

---

### Run Codestral locally with Ollama

```bash
# Pull
ollama pull codestral

# Chat
ollama run codestral

# Use as completion server (port 11434)
curl http://localhost:11434/api/generate -d '{
  "model": "codestral",
  "prompt": "Write a Rust function that returns the Nth Fibonacci number using memoization."
}'
```

### Use Codestral with Continue

```jsonc
// config.json in your Continue extension
{
  "models": [
    {
      "title": "Codestral (local)",
      "provider": "ollama",
      "model": "codestral",
      "apiBase": "http://localhost:11434"
    }
  ],
  "tabAutocompleteModel": {
    "title": "Codestral Autocomplete",
    "provider": "ollama",
    "model": "codestral"
  }
}
```

### Use Codestral with Aider

```bash
# Via Mistral API (production)
export MISTRAL_API_KEY=your-key
aider --model mistral/codestral-latest

# Or via local Ollama
aider --model ollama/codestral
```

### Through LiteLLM

```python
from litellm import completion

response = completion(
    model="codestral/codestral-latest",
    messages=[{"role": "user", "content": "Refactor this Python function to use list comprehensions"}],
    api_key=os.environ["CODESTRAL_API_KEY"],
)
```

### Codestral vs general Mistral models

| Model | Specialty | Best for |
|---|---|---|
| Mistral Small | General-purpose | Chat, summarization, RAG |
| Codestral | Code-only | Tab completion, refactor, code Q&A |
| Mixtral 8x7B | Mixture-of-experts | High-throughput inference |

---

### FAQ

**Q: Is Codestral free?**
A: The Codestral 22B open-weights are free under the Mistral AI Non-Production License (research, non-commercial). For production / commercial use, call Codestral via Mistral's paid API on la-platforme.mistral.ai.

**Q: How does Codestral compare to Claude / GPT for coding?**
A: On code-specific benchmarks (HumanEval, MBPP) Codestral is competitive with Claude 3.5 Sonnet. For broad reasoning + coding combined, Claude / GPT-4 still lead. Codestral's wins are local deployment and lower latency.

**Q: Can I fine-tune Codestral?**
A: Yes — Mistral provides LoRA fine-tuning recipes for Codestral. The open-weight version can be fine-tuned with any standard tool (axolotl, unsloth, trl). Mistral's hosted fine-tuning API is also available.

---

## Source & Thanks

> Built by [Mistral AI](https://github.com/mistralai). Open-weights under Mistral AI Non-Production License.
>
> [Codestral on Hugging Face](https://huggingface.co/mistralai/Codestral-22B-v0.1) — ⭐ 1,500+

---

<!-- ZH -->

## 快速使用

1. 本地：`ollama pull codestral && ollama run codestral`
2. API：到 console.mistral.ai 拿 key，然后 `export MISTRAL_API_KEY=...`
3. 接到 Continue / Aider / LiteLLM，用下面的代码片段

---

## 简介

Codestral 是 Mistral AI 的编码专用模型 —— 220 亿参数、32K 上下文、覆盖 Python / JavaScript / Bash / Fortran 等 80+ 语言。开源权重的 Codestral 22B 在科研和非商用场景免费；生产用最新 Codestral 通过 Mistral API 或 Le Chat 调。适合 Continue / Aider 本地补全、延迟敏感的代码生成。兼容 Ollama / vLLM / llama.cpp / Continue / Aider / LiteLLM。装机时间 5 分钟（ollama pull 或拿 API key）。

---

### 用 Ollama 本地跑 Codestral

```bash
# 拉模型
ollama pull codestral

# 聊天
ollama run codestral

# 当补全服务跑（端口 11434）
curl http://localhost:11434/api/generate -d '{
  "model": "codestral",
  "prompt": "Write a Rust function that returns the Nth Fibonacci number using memoization."
}'
```

### Continue 接 Codestral

```jsonc
// Continue 扩展的 config.json
{
  "models": [
    {
      "title": "Codestral (local)",
      "provider": "ollama",
      "model": "codestral",
      "apiBase": "http://localhost:11434"
    }
  ],
  "tabAutocompleteModel": {
    "title": "Codestral Autocomplete",
    "provider": "ollama",
    "model": "codestral"
  }
}
```

### Aider 接 Codestral

```bash
# 走 Mistral API（生产）
export MISTRAL_API_KEY=your-key
aider --model mistral/codestral-latest

# 或走本地 Ollama
aider --model ollama/codestral
```

### 通过 LiteLLM

```python
from litellm import completion

response = completion(
    model="codestral/codestral-latest",
    messages=[{"role": "user", "content": "Refactor this Python function to use list comprehensions"}],
    api_key=os.environ["CODESTRAL_API_KEY"],
)
```

### Codestral 和通用 Mistral 模型对比

| 模型 | 专长 | 适合 |
|---|---|---|
| Mistral Small | 通用 | 聊天、摘要、RAG |
| Codestral | 编码专用 | Tab 补全、重构、代码问答 |
| Mixtral 8x7B | 专家混合 | 高吞吐推理 |

---

### FAQ

**Q: Codestral 免费吗？**
A: Codestral 22B 开源权重在 Mistral AI Non-Production License 下免费（科研、非商用）。生产/商用通过 Mistral 的付费 API（la-platforme.mistral.ai）调。

**Q: Codestral 跟 Claude / GPT 在编码上比怎样？**
A: 代码专项 benchmark（HumanEval、MBPP）上 Codestral 跟 Claude 3.5 Sonnet 持平。综合推理+编码 Claude / GPT-4 仍领先。Codestral 的胜场是本地部署和低延迟。

**Q: Codestral 能微调吗？**
A: 能。Mistral 给了 Codestral 的 LoRA 微调配方。开源权重版本可以用任何标准工具（axolotl / unsloth / trl）微调。Mistral 也提供托管微调 API。

---

## 来源与感谢

> Built by [Mistral AI](https://github.com/mistralai). Open-weights under Mistral AI Non-Production License.
>
> [Codestral on Hugging Face](https://huggingface.co/mistralai/Codestral-22B-v0.1) — ⭐ 1,500+


---
Source: https://tokrepo.com/en/workflows/mistral-codestral-22b-open-weight-coding-model
Author: Mistral AI