Model Providers

OpenClaw works with multiple LLM providers. Authenticate with a provider, and set your default model to provider/model.

Looking for Chat Channels (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc)? See Channels.

Venice is our recommended privacy-first inference solution: open models by default in privacy mode, with option to use proprietary models like Opus via anonymous proxy for harder tasks.

- Default: venice/llama-3.3-70b

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

See Venice AI.

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

2. Set a default model:

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

- OpenAI (API + Codex)

- Anthropic (API + Claude Code CLI)

- Qwen (OAuth)

- OpenRouter

- Vercel AI Gateway

- Moonshot AI (Kimi + Kimi Coding)

- OpenCode Zen

- Z.AI

- Xiaomi

- GLM Models

- MiniMax

- Venice (Privacy First)

- Ollama (Local Models)

- Deepgram (Audio Transcription)

- Claude Max API Proxy - Use Claude Max/Pro subscription as an OpenAI compatible API endpoint

For a fuller catalog of providers (xAI, Groq, Mistral, etc) and advanced configuration see Model providers.