Flux RouterDocumentation

Mistral Vibe

Add FluxRouter to Mistral Vibe as a custom OpenAI-style provider in config.toml.

Mistral Vibe talks to FluxRouter over the OpenAI endpoint at https://api.fluxrouter.ai/v1, and your Flux key is the only credential it needs.

For abilities as well as models, such as reading pages and making images, add the Flux tools server with the same key if your version of the tool supports remote MCP servers.

Manual config

Add a provider entry and a model entry to ~/.vibe/config.toml:

toml
[[providers]]
name = "flux"
api_style = "openai"
api_base = "https://api.fluxrouter.ai/v1"
api_key_env = "FLUX_API_KEY"

[[models]]
name = "flux-auto"
provider = "flux"

Then export your Flux key:

bash
export FLUX_API_KEY="sk-YOUR-FLUX-KEY"

Test it

Start Vibe and send a short prompt:

bash
vibe

If the response comes back, your traffic is flowing through FluxRouter. Check your dashboard to confirm the request landed.

Notes

Keep the model set to flux-auto and Flux picks among vetted models for each request. If you want to pin a tier, point a [[models]] entry at flux-fast, flux-standard, or flux-reasoning instead. Vibe reads the key from the env var named in api_key_env, so make sure FLUX_API_KEY is exported in the shell you launch Vibe from.