Higress AI Gateway Integration

Deploy Higress AI Gateway and configure OpenClaw to use it as a unified model provider.

Quick Start

Step 1: Collect Information from User

Ask the user for the following information upfront:

1. Which LLM provider(s) to use? (at least one required)

   Commonly Used Providers:

   Provider	Parameter	Notes
   智谱 / z.ai	--zhipuai-key	Models: glm-*, Code Plan mode enabled by default
   Claude Code	--claude-code-key	Requires OAuth token from claude setup-token
   Moonshot (Kimi)	--moonshot-key	Models: moonshot-, kimi-
   Minimax	--minimax-key	Models: abab-*
   阿里云通义千问 (Dashscope)	--dashscope-key	Models: qwen*
   OpenAI	--openai-key	Models: gpt-, o1-, o3-*
   DeepSeek	--deepseek-key	Models: deepseep-*
   Grok	--grok-key	Models: grok-*

   Other Providers:

   Provider	Parameter	Notes
   Claude	--claude-key	Models: claude-*
   Google Gemini	--gemini-key	Models: gemini-*
   OpenRouter	--openrouter-key	Supports all models (catch-all)
   Groq	--groq-key	Fast inference
   Doubao (豆包)	--doubao-key	Models: doubao-*
   Mistral	--mistral-key	Models: mistral-*
   Baichuan (百川)	--baichuan-key	Models: Baichuan*
   01.AI (Yi)	--yi-key	Models: yi-*
   Stepfun (阶跃星辰)	--stepfun-key	Models: step-*
   Cohere	--cohere-key	Models: command*
   Fireworks AI	--fireworks-key	-
   Together AI	--togetherai-key	-
   GitHub Models	--github-key	-

   Cloud Providers (require additional config):

   • Azure OpenAI: --azure-key (requires service URL)
   • AWS Bedrock: --bedrock-key (requires region and access key)
   • Google Vertex AI: --vertex-key (requires project ID and region)

   Brand Name Display (z.ai / 智谱):

   • ...