Mistral AI - profClaw

Mistral AI provides high-quality models with European data residency. Codestral is particularly well-suited for code generation tasks.

Supported Models

Model	ID	Context	Tools	Notes
Mistral Large	`mistral-large-latest`	128K	Yes	Best capability
Mistral Medium	`mistral-medium-latest`	32K	Yes	Balanced
Codestral	`codestral-latest`	32K	Yes	Code-optimized
Mistral Small	`mistral-small-latest`	32K	Yes	Cost-efficient

Setup

1

Get an API key

Sign up at console.mistral.ai.

2

Set the environment variable

export MISTRAL_API_KEY=...

3

Verify

profclaw doctor --provider mistral

Environment Variables

MISTRAL_API_KEY

string

required

Your Mistral AI API key.

Configuration Example

.env
settings.yml

MISTRAL_API_KEY=...

providers:
  mistral:
    api_key: "${MISTRAL_API_KEY}"

Model Aliases

Alias	Model
`mistral`	mistral-large-latest
`mistral-medium`	mistral-medium-latest
`codestral`	codestral-latest
`mistral-local`	mistral:7b (via Ollama)

Usage Examples

profclaw chat --model mistral "Review this API design"
profclaw chat --model codestral "Generate unit tests for this function"

Notes

API endpoint: https://api.mistral.ai/v1 (OpenAI-compatible)
Mistral offers EU data residency - useful for GDPR-sensitive workloads.
codestral-latest is optimized for code completion and generation.
The local mistral-local alias runs via Ollama at no API cost.

AI Providers Overview - Compare all 37 supported providers
Ollama - Run Mistral models locally at no API cost
Cohere - Another European-headquartered provider option
profclaw provider - Add and test providers from the CLI

CohereUse Command R+ and Command R models via the Cohere API. Strong retrieval-augmented generation and enterprise search capabilities.

⌘I

Supported Models
Setup
Environment Variables
Configuration Example
Model Aliases
Usage Examples
Notes
Related