Setup guide - Documented by Goose
Use Mistral in Goose
goose lists Mistral AI as a built-in provider that needs MISTRAL_API_KEY. Configure it with goose configure > Configure Providers in the CLI, or Settings > Models > Configure providers in goose Desktop.
Last verified 6 steps2 official sources
Steps
- Step 1.
In your terminal, run:
Terminalgoose configure - Step 2.
Select Configure Providers (Change provider or update credentials) and press Enter.
- Step 3.
Choose Mistral AI as the model provider and press Enter. Use the arrow keys to move through the options, or start typing to filter the list.
- Step 4.
Enter your MISTRAL_API_KEY when prompted, then choose the model you want to use. The change takes effect the next time you start a session.
- Step 5.
Desktop alternative: open the sidebar, click Settings, open the Models tab, click Configure providers, click your provider in the list, add your API key, and click Submit.
- Step 6.
To set the model for a single session, use the run command (docs example shown; swap in a Mistral model id):
Terminalgoose run --model claude-sonnet-4-0 -t "initial prompt"
Caveats
- goose's providers table describes Mistral AI as giving access to general-purpose models, Codestral and Pixtral, but lists no model ids. The ids here come from Mistral's Models Overview.
- goose's docs: "goose configure doesn't support entering custom model names." For a model missing from the list, use goose Desktop or edit GOOSE_MODEL in config.yaml.
- The goose docs do not document the GOOSE_PROVIDER value for Mistral.
- Pixtral, mentioned in goose's table, is deprecated in Mistral's docs (pixtral-large-2411 retired 2026-05-31).
- 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 Goose?
goose lists Mistral AI as a built-in provider that needs MISTRAL_API_KEY. Configure it with goose configure > Configure Providers in the CLI, or Settings > Models > Configure providers in goose Desktop.
Which Mistral model ids work in Goose?
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.
Is this an official Mistral and Goose setup?
Goose documents this setup in its own docs. It was last checked against 2 official pages on October 17, 2026.
Sources
Last verified against 2 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.