Setup guide - Documented by Aider
Use Mistral in Aider
Aider has no dedicated Mistral page, but it documents connecting to any OpenAI-compatible endpoint with OPENAI_API_BASE and OPENAI_API_KEY plus an openai/ model prefix. Mistral documents https://api.mistral.ai/v1 as its OpenAI-compatible base URL. Aider's Other LLMs page also lists MISTRAL_API_KEY among the env vars its LiteLLM backend supports.
Last verified 2 steps4 official sources
Steps
- Step 1.
Configure your Mistral API key and Mistral's OpenAI-compatible endpoint (Aider's documented env vars, Mistral's documented base URL).
Terminal# Mac/Linux: export OPENAI_API_BASE=https://api.mistral.ai/v1 export OPENAI_API_KEY=<your_mistral_api_key> # Windows: setx OPENAI_API_BASE https://api.mistral.ai/v1 setx OPENAI_API_KEY <your_mistral_api_key> # ... restart shell after setx commands - Step 2.
Start aider in your codebase and prefix the Mistral model name with openai/.
Terminal# Change directory into your codebase cd /to/your/project # Prefix the model name with openai/ aider --model openai/mistral-medium-latest
Caveats
- This combines Aider's documented OpenAI-compatible mechanism with Mistral's documented base URL and model ids.
- Aider's Other LLMs page lists MISTRAL_API_KEY as a LiteLLM-supported variable but does not document a mistral/ model prefix or give an example. Only the openai/ path is shown verbatim here.
- Aider warns about models it is not familiar with. See its model warnings page.
- Devstral 2 (devstral-2512) was retired 2026-07-31 and replaced by mistral-medium-3-5.
More setup guides
Same tool, other providers
Related reading
- Mistral Large 4: Specs, Pricing, Benchmarks and Weights DateMistral Large 4 is a 1T-parameter multimodal MoE with 52B active, in public preview at $0.68/$2.09 per million tokens, with open weights due end of October.
- Mistral Shieldstral: A 3B Open-Weight Policy-Adaptive Moderation Model That Beats Models 7x Its SizeMistral Shieldstral is a 3B Apache 2.0 multimodal moderation model that takes your policy as a plain-language question at inference and runs on one 16GB GPU.
- Mistral Releases Robostral Navigate: An 8B Robotics Navigation ModelMistral Robostral Navigate is an 8B robotics model that navigates with only a camera and natural language commands. How it works and what the benchmarks mean.
- Leanstral 1.5: Mistral's Open Theorem-Proving Model Hits 100% on miniF2FLeanstral 1.5 is Mistral's open Apache-2.0 model for Lean 4 theorem proving. The benchmark claims, the HN pushback on its bug-finding pitch, and how to use it.
- Mistral OCR 4 and Unlimited OCR Make Document Parsing an Agent Runtime ChoiceMistral OCR 4 and Baidu's Unlimited OCR turn document parsing into a runtime choice for agents - cost per page, layout, confidence scores and self-hosting.
- Codex Custom Model Providers: GLM-5.3, Mistral and OllamaCodex only speaks the Responses API now. Tested config.toml blocks for GLM-5.3, Mistral Large 4 through a gateway, local Ollama and an internal proxy.
FAQ
How do I use Mistral in Aider?
Aider has no dedicated Mistral page, but it documents connecting to any OpenAI-compatible endpoint with OPENAI_API_BASE and OPENAI_API_KEY plus an openai/ model prefix. Mistral documents https://api.mistral.ai/v1 as its OpenAI-compatible base URL. Aider's Other LLMs page also lists MISTRAL_API_KEY among the env vars its LiteLLM backend supports.
Which Mistral model ids work in Aider?
The official docs read for this guide list mistral-medium-3-5, mistral-medium-latest, mistral-small-2603, mistral-small-latest, codestral-2508 and codestral-latest. Requests go to https://api.mistral.ai/v1.
Is this an official Mistral and Aider setup?
Aider documents this setup in its own docs. It was last checked against 4 official pages on October 17, 2026.
Sources
Last verified against 4 official pages.
Newsletter
New models, set up the day they ship
One email per week. New model releases, the coding tools that support them and how to wire them up.