Setup guide - Documented by GitHub Copilot
Use Mistral in GitHub Copilot
Copilot Chat in VS Code supports Bring Your Own Key through a Custom Endpoint provider that speaks Chat Completions. Mistral documents POST /v1/chat/completions at https://api.mistral.ai, so a Mistral model can be added in chatLanguageModels.json with vendor customendpoint and apiType chat-completions.
Last verified 4 steps4 official sources
Steps
- Step 1.
Open the Language Models editor: select Manage Language Models (gear icon) in the model picker, or run Chat: Manage Language Models from the Command Palette.
- Step 2.
Select Add Models, then select Custom Endpoint. Enter a group name, then a display name and API key, and select the API type Chat Completions.
- Step 3.
VS Code opens chatLanguageModels.json. Configure the model using the documented Custom Endpoint properties with Mistral's endpoint and a model id, then save.
JSON[ { "name": "Mistral", "vendor": "customendpoint", "apiKey": "${input:mistralApiKey}", "apiType": "chat-completions", "models": [ { "id": "mistral-medium-latest", "name": "Mistral Medium 3.5", "url": "https://api.mistral.ai/v1/chat/completions", "toolCalling": true, "vision": true } ] } ] - Step 4.
Select the model from the model picker in chat. If it does not appear right away, restart VS Code.
Caveats
- This combines VS Code's documented Custom Endpoint config with Mistral's documented Chat Completions endpoint and model ids. VS Code's docs do not name Mistral.
- Set maxInputTokens and maxOutputTokens (or contextWindow) from Mistral's docs. Mistral Medium 3.5 lists a 256k context; Mistral does not state a max output size on the model page.
- vision: true reflects Mistral's listing of text and image input for Medium 3.5. Set it to false for codestral-latest, which is text-only.
- BYOK covers chat and utility tasks only. Inline suggestions (code completions), semantic search and embeddings still need a GitHub account, so Codestral cannot be used for Copilot completions this way.
- Copilot Business and Enterprise admins must enable the Bring Your Own Language Model Key in VS Code policy.
- The Custom Endpoint provider replaces the deprecated OpenAI Compatible provider. The github.copilot.chat.customOAIModels setting is deprecated.
- 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 GitHub Copilot?
Copilot Chat in VS Code supports Bring Your Own Key through a Custom Endpoint provider that speaks Chat Completions. Mistral documents POST /v1/chat/completions at https://api.mistral.ai, so a Mistral model can be added in chatLanguageModels.json with vendor customendpoint and apiType chat-completions.
Which Mistral model ids work in GitHub Copilot?
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 GitHub Copilot setup?
GitHub Copilot 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.
- code.visualstudio.comhttps://code.visualstudio.com/docs/agent-customization/language-models
- docs.mistral.aihttps://docs.mistral.ai/api
- docs.mistral.aihttps://docs.mistral.ai/models/mistral-medium-3-5-26-04
- docs.mistral.aihttps://docs.mistral.ai/models
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.