Model Providers Quick Start

OpenClaw can use multiple LLM providers. Choose a provider to complete authentication, then set the default model to ''provider/model''.

Venice is our recommended privacy-first inference solution: open-source models available by default in privacy mode, and can also choose Opus via anonymous proxy for the hardest tasks.

- Default: ''venice/llama-3.3-70b''

- Best overall: ''venice/claude-opus-45'' (Opus is still the strongest)

See ''Venice AI'' for details.

1. Authenticate with a provider (usually via ''openclaw onboard'').

2. Set the default model:

{
  agents: { defaults: { model: { primary: "anthropic/claude-opus-4-5" } } },
}

- ''OpenAI (API + Codex)''

- ''Anthropic (API + Claude Code CLI)''

- ''OpenRouter''

- ''Vercel AI Gateway''

- ''Moonshot AI (Kimi + Kimi Coding)''

- ''Synthetic''

- ''OpenCode Zen''

- ''Z.AI''

- ''GLM Models''

- ''MiniMax''

- ''Venice (Venice AI)''

- ''Amazon Bedrock''

For a more complete provider directory (xAI, Groq, Mistral, etc.) and advanced configuration, see ''Model providers''.