Model Provider Quickstart for OpenClaw
Learn how to set up model providers in OpenClaw, including authentication and default model assignment. This page lists supported providers and links to their setup guides.
Read this when
- You want to choose a model provider
- You want quick setup examples for LLM auth + model selection
Choose a provider, complete authentication, then assign the default model using provider/model.
Quick start (two steps)
- Complete authentication with the provider, typically through
openclaw onboard. - Configure the default model:
{
agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
}
Supported providers (starter set)
- Alibaba Model Studio
- Amazon Bedrock
- Anthropic (API + Claude CLI)
- Baseten (Inkling + Model APIs)
- BytePlus (International)
- Chutes
- Cloudflare AI Gateway
- Cohere
- ComfyUI
- DeepInfra
- fal
- Fireworks
- MiniMax
- Mistral
- Moonshot AI (Kimi + Kimi Coding)
- NovitaAI
- OpenAI (API + Codex)
- OpenCode (Zen + Go)
- OpenRouter
- Qianfan
- Qwen
- Runway
- StepFun
- Synthetic
- Venice (Venice AI)
- Vercel AI Gateway
- xAI
- Z.AI (GLM)
For the complete list of providers along with advanced settings, refer to the Provider directory and Model providers.
Additional provider variants
anthropic-vertex- set up@openclaw/anthropic-vertex-providerto enable implicit Anthropic on Google Vertex support when Vertex credentials exist; no separate onboarding authentication selection is neededcopilot-proxy- local VS Code Copilot Proxy bridge; invoke withopenclaw onboard --auth-choice copilot-proxygoogle-gemini-cli- optional explicit runtime for canonicalgoogle/*models; a localgeminiinstallation plus a supported Google AI Studio API-key profile is required; new Gemini CLI or Antigravity OAuth setup is unavailable