Skip to main content
Kilo Gateway routes requests to many models behind a single OpenAI-compatible endpoint and API key.
PropertyValue
Providerkilocode
AuthKILOCODE_API_KEY
APIOpenAI-compatible
Base URLhttps://api.kilo.ai/api/gateway/

​
Install plugin

openclaw plugins install @openclaw/kilocode-provider
openclaw gateway restart

​
Setup

1

Create an account

Go to app.kilo.ai, sign in or create an account, then generate an API key.
2

Run onboarding

openclaw onboard --auth-choice kilocode-api-key
Or set the environment variable directly:
export KILOCODE_API_KEY="<your-kilocode-api-key>" # pragma: allowlist secret
3

Verify the model is available

openclaw models list --provider kilocode

​
Default model and catalog

The default model is kilocode/kilo/auto, a provider-owned smart-routing model. OpenClaw does not publish a task-to-upstream-model mapping for it; routing behind kilo/auto is owned by Kilo Gateway. At startup OpenClaw queries GET https://api.kilo.ai/api/gateway/models and merges discovered models ahead of a static fallback catalog. The static fallback contains only kilocode/kilo/auto (Kilo Auto, input: ["text", "image"], reasoning: true, contextWindow: 1000000, maxTokens: 128000). Any model on the gateway is addressable as kilocode/<upstream-id> (for example kilocode/anthropic/claude-sonnet-4, kilocode/openai/gpt-5.5). Run /models kilocode or openclaw models list --provider kilocode to see the full discovered list.

​
Config example

{
  env: { KILOCODE_API_KEY: "<your-kilocode-api-key>" }, // pragma: allowlist secret
  agents: {
    defaults: {
      model: { primary: "kilocode/kilo/auto" },
    },
  },
}

​
Behavior notes

Kilo Gateway is OpenRouter-compatible, so it uses the proxy-style OpenAI-compatible request path rather than native OpenAI request shaping (no store, no OpenAI reasoning-effort payload).
  • Gemini-backed Kilo refs stay on the proxy-Gemini path: OpenClaw sanitizes Gemini thought signatures there but does not enable native Gemini replay validation or bootstrap rewrites.
  • Requests use a Bearer token built from your API key.
The Kilo stream wrapper adds an X-KILOCODE-FEATURE request header (default openclaw, override with the KILOCODE_FEATURE env var) and normalizes reasoning-effort payloads for models that support it.
kilocode/kilo/auto and x-ai/* refs skip reasoning-effort injection. Use a concrete model ref such as kilocode/anthropic/claude-sonnet-4 if you need reasoning support.
  • If model discovery fails at startup, OpenClaw falls back to the static catalog containing kilocode/kilo/auto.
  • Confirm your API key is valid and that your Kilo account has the desired models enabled.
  • When Gateway runs as a daemon, ensure KILOCODE_API_KEY is available to that process (for example in ~/.openclaw/.env or via env.shellEnv).

Model selection

Choosing providers, model refs, and failover behavior.

Configuration reference

Full OpenClaw configuration reference.

Kilo Gateway

Kilo Gateway dashboard, API keys, and account management.