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.

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 FluxRouter picks the lane 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.