Show HN: Claudette - Mistral models in Claude Code

A developer released Claudette, an open-source wrapper that runs Anthropic's Claude Code CLI against Mistral models by starting a local proxy on port 4791 that translates Claude Code's requests to Mistral's API. Claudette defaults to mistral-large-latest for main work and mistral-small-latest for background tasks, keeps its own config directory so existing Claude Code logins and history are untouched, and is installed via a curl script; the author notes Anthropic does not support running Claude Code on non-Claude models, so the tool is best-effort. Tested on macOS only, Claudette lacks extended thinking, prompt caching, Remote Control, voice mode and fast mode, and Codestral and mistral-code-latest are listed but cannot call tools, which Claude Code depends on.

Run Claude Code https://code.claude.com with Mistral models. claudette is a drop-in wrapper around claude . It starts a small local proxy that translates Claude Code's requests for Mistral's API, then runs claude against it. It keeps its own config directory, so your regular Claude Code setup, login and history are left alone. Anthropic doesn't support running Claude Code on non-Claude models, so treat this as best-effort. The limitations are listed below. - Claude Code https://code.claude.com - uv https://docs.astral.sh/uv/ - A Mistral API key from console.mistral.ai https://console.mistral.ai Tested on macOS. Linux should work but hasn't been tested, and Windows isn't supported. curl -fsSL https://raw.githubusercontent.com/raed667/claudette/main/install.sh | bash The installer asks for your Mistral API key and stores it in ~/.config/claudette/mistral api key . If you skip the prompt, run the command again later or export MISTRAL API KEY instead. To update, run claudette update or the same install command. claudette takes the same flags and subcommands as claude : claudette claudette -p "explain this repo" claudette --continue The proxy starts on first use and keeps running in the background. Use claudette proxy stop to shut it down, or claudette proxy logs when requests fail. The status line shows the model, how much of the context is used before Claude Code compacts, an estimated cost at Mistral's prices, and the current folder and branch: mistral-large | ctx 42k/256k 16% | ~$0.96 | claudette main The cost is the session's spend so far at Mistral's list prices, cached input included. It doesn't count web searches or the extra requests auto mode makes to check tool calls. A trailing + means part of the session used a model without a known price. Mistral doesn't publish one for Medium, so a Medium-only session shows no cost. If you've set your own statusLine in ~/.claudette/settings.json , yours is used instead. The main model is mistral-large-latest , and background tasks use mistral-small-latest . Any chat model your key can use works. claudette models lists them with their context sizes: claudette models CLAUDETTE MODEL=ministral-14b-latest claudette The list is cached for a day; claudette models --refresh fetches it again. Large, Medium and Small are the ones that have been tested. Codestral and mistral-code-latest are listed but don't call tools, which Claude Code depends on. Inside a session, /model lists Large, Medium and Small, plus your CLAUDETTE MODEL if it's something else, and /model <name takes any other model. Compaction is tuned to the model you start with, so prefer CLAUDETTE MODEL when switching to a model with a smaller context window. If you've set your own modelPicker in ~/.claudette/settings.json , yours is used instead. | Variable | Default | | |---|---|---| | MISTRAL API KEY | | Overrides the key file | | CLAUDETTE MODEL | mistral-large-latest | Main model | | CLAUDETTE FAST MODEL | mistral-small-latest | Background tasks | | CLAUDETTE COMPACT WINDOW | model's context, up to 256000 | Tokens before Claude Code compacts the conversation | | CLAUDETTE PORT | 4791 | Local proxy port | | CLAUDETTE STATUSLINE | 1 | Set to 0 to turn off the default status line | - Web search goes through Mistral's own search instead of Anthropic's. You get a summarised answer with source links rather than raw results, and searches are billed by Mistral. - Extended thinking, prompt caching, Remote Control, voice mode and fast mode aren't available. - Your global ~/.claude/CLAUDE.md is still loaded, which means its contents are sent to Mistral. How it works, testing and known quirks are in CONTRIBUTING.md https://github.com/raed667/claudette/blob/main/CONTRIBUTING.md . claudette is a hobby project. I wanted Claude Code's workflow with Mistral's models, so I built it for myself and published it in case someone else wants the same thing. I'm not affiliated with Anthropic or Mistral AI, and neither company endorses or supports it. Claude, Claude Code and Mistral are trademarks of their owners. claudette doesn't include or modify Claude Code; it launches your own install against Mistral's public API with your own key, so both companies' terms still apply to how you use them.