Kimi CLI

Add FluxRouter as an OpenAI provider in Kimi CLI's config.toml at the /v1 base URL.

Kimi CLI talks to FluxRouter through an OpenAI provider, which uses the /v1 endpoint. 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 [providers.flux] block and a matching [models.flux-auto] entry to ~/.kimi/config.toml:

toml
[providers.flux]
type = "openai"
base_url = "https://api.fluxrouter.ai/v1"
api_key = "$FLUX_API_KEY"

[models.flux-auto]
provider = "flux"
model = "flux-auto"

Then export your Flux key:

bash
export FLUX_API_KEY=sk-YOUR-FLUX-KEY

Test it

Run kimi and send a prompt. A reply confirms the connection. Check your FluxRouter dashboard to confirm the request landed.

Notes

flux-auto is the default and routes each request for you. If you want to pin a single lane, add a matching model entry for flux-fast, flux-standard, or flux-reasoning.