Add OpenRouter support + 15+ popular models (Qwen, Grok, MiMo, Seed, Nemotron, GLM, Mercury, etc.)

.env.example

@@ -55,6 +55,42 @@ LLM_API_KEY=your_api_key_here
 #   - groq/mixtral-8x7b-32768
 #   - groq/llama2-70b-4096
 #
+# Qwen:
+#   - qwen/qwen3.6-plus-preview (free, 1M context)
+#   - qwen/qwen3.5-35b-a3b
+#   - qwen/qwen3.5-9b
+#
+# xAI Grok:
+#   - x-ai/grok-4.20-beta
+#   - x-ai/grok-4.20-multi-agent-beta
+#
+# NVIDIA:
+#   - nvidia/nemotron-3-super-120b-a12b
+#   - nvidia/nemotron-3-super-120b-a12b (free)
+#
+# Reka:
+#   - reka/reka-edge
+#
+# Xiaomi:
+#   - xiaomi/mimo-v2-pro (1M context)
+#   - xiaomi/mimo-v2-omni (256K context, multimodal)
+#
+# ByteDance Seed:
+#   - bytedance-seed/seed-2.0-lite
+#   - bytedance-seed/seed-2.0-mini
+#
+# Z.ai GLM:
+#   - z-ai/glm-5-turbo
+#
+# KwaiPilot:
+#   - kwaipilot/kat-coder-pro-v2
+#
+# OpenRouter (any model via OpenRouter proxy):
+#   - openrouter/google/lyria-3-pro-preview (music generation)
+#   - openrouter/inception/mercury-2 (fast reasoning)
+#   Note: With OpenRouter, you can access 100+ models with a single API key!
+#   See https://openrouter.ai/models for complete list
+#
 # Or any other provider supported by OpenClaw (format: provider/model-name)
 LLM_MODEL=anthropic/claude-sonnet-4-5
 

README.md

@@ -189,6 +189,79 @@ LLM_MODEL=groq/mixtral-8x7b-32768
 Models: `groq/mixtral-8x7b-32768` · `groq/llama2-70b-4096`
 Get key from: [Groq Console](https://console.groq.com)
 
+### Qwen
+```
+LLM_API_KEY=your_qwen_api_key
+LLM_MODEL=qwen/qwen3.6-plus-preview
+```
+Models: `qwen/qwen3.6-plus-preview` (free!) · `qwen/qwen3.5-35b-a3b` · `qwen/qwen3.5-9b`
+Get key from: [Qwen API](https://dashscope.aliyun.com)
+
+### xAI (Grok)
+```
+LLM_API_KEY=your_xai_api_key
+LLM_MODEL=x-ai/grok-4.20-beta
+```
+Models: `x-ai/grok-4.20-beta` · `x-ai/grok-4.20-multi-agent-beta`
+Get key from: [xAI Console](https://console.x.ai)
+
+### NVIDIA (Nemotron)
+```
+LLM_API_KEY=your_nvidia_api_key
+LLM_MODEL=nvidia/nemotron-3-super-120b-a12b
+```
+Models: `nvidia/nemotron-3-super-120b-a12b` · `nvidia/nemotron-3-super-120b-a12b` (free)
+Get key from: [NVIDIA API](https://api.nvidia.com)
+
+### Xiaomi (MiMo)
+```
+LLM_API_KEY=your_xiaomi_api_key
+LLM_MODEL=xiaomi/mimo-v2-pro
+```
+Models: `xiaomi/mimo-v2-pro` (1M context) · `xiaomi/mimo-v2-omni` (multimodal)
+Get key from: [Xiaomi](https://xiaoai.xiaomi.com)
+
+### ByteDance (Seed)
+```
+LLM_API_KEY=your_bytedance_api_key
+LLM_MODEL=bytedance-seed/seed-2.0-lite
+```
+Models: `bytedance-seed/seed-2.0-lite` · `bytedance-seed/seed-2.0-mini`
+Get key from: [ByteDance](https://www.volcengine.com)
+
+### Z.ai (GLM)
+```
+LLM_API_KEY=your_zai_api_key
+LLM_MODEL=z-ai/glm-5-turbo
+```
+Models: `z-ai/glm-5-turbo`
+Get key from: [Z.ai](https://z.ai)
+
+### OpenRouter (100+ models via single API)
+```
+LLM_API_KEY=your_openrouter_api_key
+LLM_MODEL=openrouter/google/lyria-3-pro-preview
+```
+**Popular models via OpenRouter:**
+- `openrouter/openai/gpt-5.4-pro` — Latest OpenAI (1M context)
+- `openrouter/openai/gpt-5.4-mini` — Fast, efficient OpenAI
+- `openrouter/google/gemini-3.1-flash-lite-preview` — Google's latest
+- `openrouter/anthropic/claude-opus-4-6` — Latest Claude via OpenRouter
+- `openrouter/mistral/mistral-small-2603` — Mistral's latest
+- `openrouter/inception/mercury-2` — Ultra-fast reasoning (1000 tok/sec)
+- `openrouter/qwen/qwen3.6-plus-preview` — Free tier available!
+- `openrouter/x-ai/grok-4.20-beta` — xAI's latest Grok
+- `openrouter/nvidia/nemotron-3-super-120b-a12b` — NVIDIA's powerhouse
+- `openrouter/xiaomi/mimo-v2-pro` — Xiaomi's 1M context model
+
+**Why OpenRouter?**
+- Single API key for 100+ models
+- Unified pricing and routing
+- Auto-fallback to other models
+- No vendor lock-in
+
+Get key from: [OpenRouter.ai](https://openrouter.ai) (free tier available!)
+
 ### Any Other Provider
 HuggingClaw supports **any LLM provider** that OpenClaw supports. Just use:
 ```

start.sh

@@ -40,7 +40,9 @@ if [[ "$LLM_MODEL" == "anthropic/gemini"* ]]; then
 fi
 
 # Auto-detect and set provider-specific API key from model name
-if [[ "$LLM_MODEL" == "google/"* ]]; then
+if [[ "$LLM_MODEL" == "openrouter/"* ]]; then
+  export OPENROUTER_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "google/"* ]]; then
   export GOOGLE_API_KEY="$LLM_API_KEY"
 elif [[ "$LLM_MODEL" == "openai/"* ]]; then
   export OPENAI_API_KEY="$LLM_API_KEY"
@@ -50,12 +52,30 @@ elif [[ "$LLM_MODEL" == "moonshot/"* ]]; then
   export MOONSHOT_API_KEY="$LLM_API_KEY"
 elif [[ "$LLM_MODEL" == "minimax/"* ]]; then
   export MINIMAX_API_KEY="$LLM_API_KEY"
-elif [[ "$LLM_MODEL" == "mistral/"* ]]; then
+elif [[ "$LLM_MODEL" == "mistral/"* ]] || [[ "$LLM_MODEL" == "mistralai/"* ]]; then
   export MISTRAL_API_KEY="$LLM_API_KEY"
 elif [[ "$LLM_MODEL" == "cohere/"* ]]; then
   export COHERE_API_KEY="$LLM_API_KEY"
 elif [[ "$LLM_MODEL" == "groq/"* ]]; then
   export GROQ_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "qwen/"* ]]; then
+  export QWEN_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "x-ai/"* ]] || [[ "$LLM_MODEL" == "xai/"* ]]; then
+  export XAI_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "nvidia/"* ]]; then
+  export NVIDIA_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "reka/"* ]]; then
+  export REKA_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "bytedance/"* ]] || [[ "$LLM_MODEL" == "seed/"* ]]; then
+  export BYTEDANCE_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "kwaipilot/"* ]]; then
+  export KWAIPILOT_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "z-ai/"* ]]; then
+  export ZAI_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "inception/"* ]]; then
+  export INCEPTION_API_KEY="$LLM_API_KEY"
+elif [[ "$LLM_MODEL" == "xiaomi/"* ]]; then
+  export XIAOMI_API_KEY="$LLM_API_KEY"
 else
   # Default to Anthropic for claude/* or anthropic/* models
   export ANTHROPIC_API_KEY="$LLM_API_KEY"