OpenClaw can use many LLM providers. Pick a provider, authenticate, then set the
default model as provider/model.
Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See Channels.
Quick start
- Authenticate with the provider (usually via
openclaw onboard). - Set the default model:
{
agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
}
Provider docs
- Alibaba Model Studio - Amazon Bedrock - Amazon Bedrock Mantle - Anthropic (API + Claude CLI) - Arcee AI (Trinity models) - Azure Speech - BytePlus (International) - Cerebras - Chutes - Cloudflare AI Gateway - ComfyUI - DeepSeek - ElevenLabs - fal - Fireworks - GitHub Copilot - GLM models - Google (Gemini) - Gradium - Groq (LPU inference) - Hugging Face (Inference) - inferrs (local models) - Kilocode - LiteLLM (unified gateway) - LM Studio (local models) - MiniMax - Mistral - Moonshot AI (Kimi + Kimi Coding) - NVIDIA - Ollama (cloud + local models) - OpenAI (API + Codex) - OpenCode - OpenCode Go - OpenRouter - Perplexity (web search) - Qianfan - Qwen Cloud - Runway - SenseAudio - SGLang (local models) - StepFun - Synthetic - Tencent Cloud (TokenHub) - Together AI - Venice (Venice AI, privacy-focused) - Vercel AI Gateway - vLLM (local models) - Volcengine (Doubao) - Vydra - xAI - Xiaomi - Z.AI
Shared overview pages
- Additional bundled variants - Anthropic Vertex, Copilot Proxy, and Gemini CLI OAuth
- Image Generation - Shared
image_generatetool, provider selection, and failover - Music Generation - Shared
music_generatetool, provider selection, and failover - Video Generation - Shared
video_generatetool, provider selection, and failover
Transcription providers
Community tools
- Claude Max API Proxy - Community proxy for Claude subscription credentials (verify Anthropic policy/terms before use)
For the full provider catalog (xAI, Groq, Mistral, etc.) and advanced configuration, see Model providers.