Fix all provider names to match OpenClaw system (zai, moonshot, mistral, xai, opencode, etc.)

.env.example

@@ -9,134 +9,119 @@
 # - Anthropic: sk-ant-v0-...
 # - OpenAI: sk-...
 # - Google: AIzaSy...
+# - OpenRouter: sk-or-v1-... (300+ models via single key)
 LLM_API_KEY=your_api_key_here
 
 # [REQUIRED] LLM model to use (format: provider/model-name)
 # Auto-detects provider from prefix — any provider is supported!
-# Model IDs sourced from https://openrouter.ai/api/v1/models
+# Provider IDs from OpenClaw docs: docs.openclaw.ai/concepts/model-providers
 #
-# ── Top-Tier Providers ──
+# ── Core Providers ──
 #
-# Anthropic Claude:
+# Anthropic (ANTHROPIC_API_KEY):
 #   - anthropic/claude-opus-4-6
 #   - anthropic/claude-sonnet-4-6
 #   - anthropic/claude-sonnet-4-5
 #   - anthropic/claude-haiku-4-5
 #
-# OpenAI:
-#   - openai/gpt-5.4-pro (1M context)
-#   - openai/gpt-5.4 (1M context)
+# OpenAI (OPENAI_API_KEY):
+#   - openai/gpt-5.4-pro
+#   - openai/gpt-5.4
 #   - openai/gpt-5.4-mini
 #   - openai/gpt-5.4-nano
 #   - openai/gpt-4.1
 #   - openai/gpt-4.1-mini
-#   - openai/gpt-4.1-nano
 #
-# Google Gemini:
+# Google Gemini (GEMINI_API_KEY):
 #   - google/gemini-3.1-pro-preview
-#   - google/gemini-3.1-flash-lite-preview
+#   - google/gemini-3-flash-preview
 #   - google/gemini-2.5-pro
 #   - google/gemini-2.5-flash
 #
-# DeepSeek:
+# DeepSeek (DEEPSEEK_API_KEY):
 #   - deepseek/deepseek-v3.2
 #   - deepseek/deepseek-r1-0528
 #   - deepseek/deepseek-r1
-#   - deepseek/deepseek-chat-v3.1
 #
-# ── Chinese/Asian Providers ──
+# ── OpenCode Providers ──
 #
-# Qwen (Alibaba):
-#   - qwen/qwen3.6-plus-preview:free (1M context, free!)
-#   - qwen/qwen3-max
-#   - qwen/qwen3-coder
-#   - qwen/qwen3.5-397b-a17b
-#   - qwen/qwen3.5-35b-a3b
-#
-# Z.ai (GLM):
-#   - z-ai/glm-5
-#   - z-ai/glm-5-turbo
-#   - z-ai/glm-4.7
-#   - z-ai/glm-4.7-flash
-#   - z-ai/glm-4.5-air:free (free!)
-#
-# Moonshot (Kimi):
-#   - moonshotai/kimi-k2.5
-#   - moonshotai/kimi-k2
-#   - moonshotai/kimi-k2-thinking
-#
-# Xiaomi (MiMo):
-#   - xiaomi/mimo-v2-pro (1M context)
-#   - xiaomi/mimo-v2-omni (multimodal)
-#   - xiaomi/mimo-v2-flash
-#
-# ByteDance Seed:
-#   - bytedance-seed/seed-2.0-lite
-#   - bytedance-seed/seed-2.0-mini
-#
-# Baidu (ERNIE):
-#   - baidu/ernie-4.5-300b-a47b
-#   - baidu/ernie-4.5-21b-a3b
-#
-# Tencent:
-#   - tencent/hunyuan-a13b-instruct
-#
-# StepFun:
-#   - stepfun/step-3.5-flash
-#   - stepfun/step-3.5-flash:free (free!)
+# OpenCode Zen — tested & verified models (OPENCODE_API_KEY):
+#   - opencode/claude-opus-4-6
+#   - opencode/gpt-5.4
+#   Get key from: https://opencode.ai/auth
 #
-# ── Western Providers ──
+# OpenCode Go — low-cost open models (OPENCODE_API_KEY):
+#   - opencode-go/kimi-k2.5
 #
-# Mistral:
-#   - mistralai/mistral-large-2512
-#   - mistralai/mistral-medium-3.1
-#   - mistralai/mistral-small-2603
-#   - mistralai/devstral-medium (coding)
-#   - mistralai/codestral-2508
-#
-# xAI (Grok):
-#   - x-ai/grok-4.20-beta
-#   - x-ai/grok-4.20-multi-agent-beta
-#   - x-ai/grok-4.1-fast
-#   - x-ai/grok-4
-#
-# Meta (Llama):
-#   - meta-llama/llama-4-maverick
-#   - meta-llama/llama-4-scout
-#   - meta-llama/llama-3.3-70b-instruct
-#
-# NVIDIA:
-#   - nvidia/nemotron-3-super-120b-a12b
-#   - nvidia/nemotron-3-super-120b-a12b:free (free!)
+# ── Gateway/Router Providers ──
 #
-# Cohere:
-#   - cohere/command-a
-#   - cohere/command-r-plus-08-2024
+# OpenRouter — 300+ models via single API key (OPENROUTER_API_KEY):
+#   - openrouter/anthropic/claude-sonnet-4-6
+#   - openrouter/openai/gpt-5.4
+#   - openrouter/deepseek/deepseek-v3.2
+#   - openrouter/meta-llama/llama-3.3-70b-instruct:free
+#   Get key from: https://openrouter.ai
 #
-# Perplexity:
-#   - perplexity/sonar-deep-research
-#   - perplexity/sonar-pro
+# Kilo Gateway (KILOCODE_API_KEY):
+#   - kilocode/anthropic/claude-opus-4.6
 #
-# MiniMax:
+# ── Chinese/Asian Providers ──
+#
+# Z.ai / GLM (ZAI_API_KEY) — OpenClaw normalizes z-ai/z.ai → zai:
+#   - zai/glm-5
+#   - zai/glm-5-turbo
+#   - zai/glm-4.7
+#   - zai/glm-4.7-flash
+#
+# Moonshot / Kimi (MOONSHOT_API_KEY):
+#   - moonshot/kimi-k2.5
+#   - moonshot/kimi-k2-thinking
+#
+# MiniMax (MINIMAX_API_KEY):
 #   - minimax/minimax-m2.7
 #   - minimax/minimax-m2.5
-#   - minimax/minimax-m2.5:free (free!)
 #
-# ── Speed & Specialty ──
+# Xiaomi / MiMo (XIAOMI_API_KEY):
+#   - xiaomi/mimo-v2-pro
+#   - xiaomi/mimo-v2-omni
+#
+# Volcengine / Doubao (VOLCANO_ENGINE_API_KEY):
+#   - volcengine/doubao-seed-1-8-251228
+#   - volcengine/kimi-k2-5-260127
+#
+# BytePlus — international (BYTEPLUS_API_KEY):
+#   - byteplus/seed-1-8-251228
+#
+# ── Western Providers ──
+#
+# Mistral (MISTRAL_API_KEY):
+#   - mistral/mistral-large-latest
+#   - mistral/mistral-small-2603
+#   - mistral/devstral-medium
+#
+# xAI / Grok (XAI_API_KEY):
+#   - xai/grok-4.20-beta
+#   - xai/grok-4
+#
+# NVIDIA (NVIDIA_API_KEY):
+#   - nvidia/nemotron-3-super-120b-a12b
+#
+# Groq (GROQ_API_KEY):
+#   - groq/mixtral-8x7b-32768
+#
+# Cohere (COHERE_API_KEY):
+#   - cohere/command-a
 #
-# Inception (ultra-fast reasoning):
-#   - inception/mercury-2 (1000+ tok/sec)
-#   - inception/mercury-coder
+# Together (TOGETHER_API_KEY):
+#   - together/meta-llama/llama-3.3-70b-instruct
 #
-# Amazon:
-#   - amazon/nova-premier-v1
-#   - amazon/nova-pro-v1
+# Cerebras (CEREBRAS_API_KEY):
+#   - cerebras/zai-glm-4.7
 #
-# ── OpenRouter (100+ models via single API key) ──
-# Use any model above via OpenRouter with a single API key!
-# See https://openrouter.ai/models for complete list
+# HuggingFace Inference (HUGGINGFACE_HUB_TOKEN):
+#   - huggingface/deepseek-ai/DeepSeek-R1
 #
-# Or any other provider — format: provider/model-name (auto-detected)
+# Or any other OpenClaw-supported provider (format: provider/model-name)
 LLM_MODEL=anthropic/claude-sonnet-4-5
 
 # [REQUIRED] Gateway authentication token
@@ -144,100 +129,44 @@ LLM_MODEL=anthropic/claude-sonnet-4-5
 GATEWAY_TOKEN=your_gateway_token_here
 
 # ── OPTIONAL: Telegram Integration ──
-# Enable Telegram bot integration
 # Get bot token from: https://t.me/BotFather
 TELEGRAM_BOT_TOKEN=your_bot_token_here
 
-# Single user ID for DM access
-# Get your ID from: https://t.me/userinfobot
+# Single user ID (from https://t.me/userinfobot)
 TELEGRAM_USER_ID=123456789
 
 # Multiple user IDs (comma-separated for team access)
 # TELEGRAM_USER_IDS=123456789,987654321,555555555
 
 # ── OPTIONAL: Workspace Backup to HF Dataset ──
-# Enable automatic workspace backup & restore
-# Your HuggingFace username
 HF_USERNAME=your_hf_username
-
-# HuggingFace API token (with write access)
-# Get from: https://huggingface.co/settings/tokens
 HF_TOKEN=hf_your_token_here
 
-# Name of the backup dataset (auto-created if missing)
+# Backup dataset name (auto-created if missing)
 # Default: huggingclaw-backup
 BACKUP_DATASET_NAME=huggingclaw-backup
 
-# Git commit email for workspace syncs
-# Default: openclaw@example.com
+# Git commit identity for workspace syncs
 WORKSPACE_GIT_USER=openclaw@example.com
-
-# Git commit name for workspace syncs
-# Default: OpenClaw Bot
 WORKSPACE_GIT_NAME=OpenClaw Bot
 
-# ── OPTIONAL: Background Services Configuration ──
-# Keep-alive ping interval in seconds (prevents HF Spaces sleep)
-# Default: 300 (5 minutes)
-# Set to 0 to disable (not recommended on HF Spaces)
+# ── OPTIONAL: Background Services ──
+# Keep-alive ping interval (seconds). Default: 300. Set 0 to disable.
 KEEP_ALIVE_INTERVAL=300
 
-# Workspace auto-sync interval in seconds
-# Default: 600 (10 minutes)
+# Workspace auto-sync interval (seconds). Default: 600.
 SYNC_INTERVAL=600
 
-# ── OPTIONAL: Advanced Configuration ──
-# Pin OpenClaw version (default: latest)
-# Example: OPENCLAW_VERSION=2026.3.24
+# ── OPTIONAL: Advanced ──
+# Pin OpenClaw version. Default: latest
 OPENCLAW_VERSION=latest
 
-# Health endpoint port (default: 7861)
+# Health endpoint port. Default: 7861
 HEALTH_PORT=7861
 
 # ════════════════════════════════════════════════════════════════
-# QUICK START CHECKLIST
-# ════════════════════════════════════════════════════════════════
-#
-# ✅ Minimum setup (3 secrets):
-#    1. LLM_API_KEY - Get from your LLM provider
-#    2. LLM_MODEL - Choose a model above
-#    3. GATEWAY_TOKEN - Run: openssl rand -hex 32
-#
-# ✅ Add Telegram (2 more secrets):
-#    4. TELEGRAM_BOT_TOKEN - From @BotFather
-#    5. TELEGRAM_USER_ID - From @userinfobot
-#
-# ✅ Enable Backup (2 more secrets):
-#    6. HF_USERNAME - Your HF account name
-#    7. HF_TOKEN - From HF Settings → Tokens
-#
-# ════════════════════════════════════════════════════════════════
-# DEPLOYMENT OPTIONS
-# ════════════════════════════════════════════════════════════════
-#
-# 📦 HuggingFace Spaces (Recommended):
-#    - Click "Duplicate this Space"
-#    - Go to Settings → Secrets
-#    - Add LLM_API_KEY, LLM_MODEL, GATEWAY_TOKEN
-#    - Deploy (automatic!)
-#
-# 🐳 Docker Local:
-#    docker build -t huggingclaw .
-#    docker run -p 7860:7860 --env-file .env huggingclaw
-#
-# 💻 Direct (without Docker):
-#    npm install -g openclaw@latest
-#    export $(cat .env | xargs)
-#    bash start.sh
-#
-# ════════════════════════════════════════════════════════════════
-# VERIFY YOUR SETUP
-# ════════════════════════════════════════════════════════════════
-#
-# After deployment, check:
-# 1. Logs for "🦞 HuggingClaw Gateway" banner
-# 2. Health endpoint: curl https://YOUR-SPACE-URL.hf.space/health
-# 3. Control UI: https://YOUR-SPACE-URL.hf.space
-# 4. (If Telegram) DM your bot to test
-#
+# QUICK START: Only 3 secrets required!
+#   1. LLM_API_KEY    → From your LLM provider
+#   2. LLM_MODEL      → Pick a model above
+#   3. GATEWAY_TOKEN   → Run: openssl rand -hex 32
 # ════════════════════════════════════════════════════════════════

README.md

@@ -118,7 +118,7 @@ See **`.env.example`** for the complete reference with examples.
 
 ## 🤖 LLM Provider Setup
 
-Just set `LLM_MODEL` with the correct provider prefix — **any provider is supported**! The provider is auto-detected from the model name. All model IDs sourced from [OpenRouter](https://openrouter.ai/models).
+Just set `LLM_MODEL` with the correct provider prefix — **any provider is supported**! The provider is auto-detected from the model name. All provider IDs from [OpenClaw docs](https://docs.openclaw.ai/concepts/model-providers).
 
 ### Anthropic (Claude)
 ```
@@ -139,131 +139,113 @@ Models: `openai/gpt-5.4-pro` · `openai/gpt-5.4` · `openai/gpt-5.4-mini` · `op
 LLM_API_KEY=AIzaSy...
 LLM_MODEL=google/gemini-2.5-flash
 ```
-Models: `google/gemini-3.1-pro-preview` · `google/gemini-3.1-flash-lite-preview` · `google/gemini-2.5-pro` · `google/gemini-2.5-flash`
+Models: `google/gemini-3.1-pro-preview` · `google/gemini-3-flash-preview` · `google/gemini-2.5-pro` · `google/gemini-2.5-flash`
 
 ### DeepSeek
 ```
 LLM_API_KEY=sk-...
 LLM_MODEL=deepseek/deepseek-v3.2
 ```
-Models: `deepseek/deepseek-v3.2` · `deepseek/deepseek-r1-0528` · `deepseek/deepseek-r1` · `deepseek/deepseek-chat-v3.1`
+Models: `deepseek/deepseek-v3.2` · `deepseek/deepseek-r1-0528` · `deepseek/deepseek-r1`
 Get key from: [DeepSeek Platform](https://platform.deepseek.com)
 
-### Qwen (Alibaba)
+### OpenCode Zen (tested & verified models)
 ```
-LLM_API_KEY=your_qwen_api_key
-LLM_MODEL=qwen/qwen3-max
+LLM_API_KEY=your_opencode_api_key
+LLM_MODEL=opencode/claude-opus-4-6
 ```
-Models: `qwen/qwen3.6-plus-preview:free` (free!) · `qwen/qwen3-max` · `qwen/qwen3-coder` · `qwen/qwen3.5-397b-a17b` · `qwen/qwen3.5-35b-a3b`
-Get key from: [DashScope](https://dashscope.aliyun.com)
+Models: `opencode/claude-opus-4-6` · `opencode/gpt-5.4`
+Get key from: [OpenCode.ai](https://opencode.ai/auth)
+
+### OpenCode Go (low-cost open models)
+```
+LLM_API_KEY=your_opencode_api_key
+LLM_MODEL=opencode-go/kimi-k2.5
+```
+Get key from: [OpenCode.ai](https://opencode.ai/auth)
 
 ### Z.ai (GLM)
 ```
 LLM_API_KEY=your_zai_api_key
-LLM_MODEL=z-ai/glm-5-turbo
+LLM_MODEL=zai/glm-5
 ```
-Models: `z-ai/glm-5` · `z-ai/glm-5-turbo` · `z-ai/glm-4.7` · `z-ai/glm-4.7-flash` · `z-ai/glm-4.5-air:free` (free!)
-Get key from: [Z.ai](https://z.ai)
+Models: `zai/glm-5` · `zai/glm-5-turbo` · `zai/glm-4.7` · `zai/glm-4.7-flash`
+Get key from: [Z.ai](https://z.ai) · Note: `z-ai/` and `z.ai/` prefixes auto-normalize to `zai/`
 
 ### Moonshot (Kimi)
 ```
 LLM_API_KEY=sk-...
-LLM_MODEL=moonshotai/kimi-k2.5
+LLM_MODEL=moonshot/kimi-k2.5
 ```
-Models: `moonshotai/kimi-k2.5` · `moonshotai/kimi-k2` · `moonshotai/kimi-k2-thinking`
+Models: `moonshot/kimi-k2.5` · `moonshot/kimi-k2-thinking`
 Get key from: [Moonshot API](https://platform.moonshot.cn)
 
 ### Mistral
 ```
 LLM_API_KEY=your_mistral_api_key
-LLM_MODEL=mistralai/mistral-large-2512
+LLM_MODEL=mistral/mistral-large-latest
 ```
-Models: `mistralai/mistral-large-2512` · `mistralai/mistral-medium-3.1` · `mistralai/mistral-small-2603` · `mistralai/devstral-medium` · `mistralai/codestral-2508`
+Models: `mistral/mistral-large-latest` · `mistral/mistral-small-2603` · `mistral/devstral-medium` · `mistral/codestral-2508`
 Get key from: [Mistral Console](https://console.mistral.ai)
 
 ### xAI (Grok)
 ```
 LLM_API_KEY=your_xai_api_key
-LLM_MODEL=x-ai/grok-4.20-beta
+LLM_MODEL=xai/grok-4.20-beta
 ```
-Models: `x-ai/grok-4.20-beta` · `x-ai/grok-4.20-multi-agent-beta` · `x-ai/grok-4.1-fast` · `x-ai/grok-4`
+Models: `xai/grok-4.20-beta` · `xai/grok-4` · `xai/grok-4.1-fast`
 Get key from: [xAI Console](https://console.x.ai)
 
-### Meta (Llama)
-```
-LLM_API_KEY=your_meta_api_key
-LLM_MODEL=meta-llama/llama-4-maverick
-```
-Models: `meta-llama/llama-4-maverick` · `meta-llama/llama-4-scout` · `meta-llama/llama-3.3-70b-instruct:free` (free!)
-
 ### MiniMax
 ```
 LLM_API_KEY=your_minimax_api_key
 LLM_MODEL=minimax/minimax-m2.7
 ```
-Models: `minimax/minimax-m2.7` · `minimax/minimax-m2.5` · `minimax/minimax-m2.5:free` (free!)
-Get key from: [MiniMax Platform](https://api.minimaxi.com)
+Models: `minimax/minimax-m2.7` · `minimax/minimax-m2.5`
+Get key from: [MiniMax Platform](https://platform.minimax.io)
 
-### NVIDIA (Nemotron)
+### NVIDIA
 ```
 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` (free!)
 Get key from: [NVIDIA API](https://api.nvidia.com)
 
-### Cohere
-```
-LLM_API_KEY=your_cohere_api_key
-LLM_MODEL=cohere/command-a
-```
-Models: `cohere/command-a` · `cohere/command-r-plus-08-2024`
-Get key from: [Cohere Dashboard](https://dashboard.cohere.com)
-
-### Perplexity
-```
-LLM_API_KEY=your_perplexity_api_key
-LLM_MODEL=perplexity/sonar-pro
-```
-Models: `perplexity/sonar-deep-research` · `perplexity/sonar-pro` · `perplexity/sonar-reasoning-pro`
-Get key from: [Perplexity API](https://www.perplexity.ai/settings/api)
-
 ### 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) · `xiaomi/mimo-v2-flash`
+Models: `xiaomi/mimo-v2-pro` · `xiaomi/mimo-v2-omni`
 
-### ByteDance (Seed)
+### Volcengine (Doubao / ByteDance)
 ```
-LLM_API_KEY=your_bytedance_api_key
-LLM_MODEL=bytedance-seed/seed-2.0-lite
+LLM_API_KEY=your_volcengine_api_key
+LLM_MODEL=volcengine/doubao-seed-1-8-251228
 ```
-Models: `bytedance-seed/seed-2.0-lite` · `bytedance-seed/seed-2.0-mini`
+Models: `volcengine/doubao-seed-1-8-251228` · `volcengine/kimi-k2-5-260127` · `volcengine/glm-4-7-251222`
 Get key from: [Volcengine](https://www.volcengine.com)
 
-### Baidu (ERNIE)
+### Groq
 ```
-LLM_API_KEY=your_baidu_api_key
-LLM_MODEL=baidu/ernie-4.5-300b-a47b
+LLM_API_KEY=your_groq_api_key
+LLM_MODEL=groq/mixtral-8x7b-32768
 ```
-Models: `baidu/ernie-4.5-300b-a47b` · `baidu/ernie-4.5-21b-a3b`
+Get key from: [Groq Console](https://console.groq.com)
 
-### Inception (Mercury — ultra-fast)
+### Cohere
 ```
-LLM_API_KEY=your_inception_api_key
-LLM_MODEL=inception/mercury-2
+LLM_API_KEY=your_cohere_api_key
+LLM_MODEL=cohere/command-a
 ```
-Models: `inception/mercury-2` (1000+ tok/sec!) · `inception/mercury-coder`
-Get key from: [Inception Labs](https://www.inceptionlabs.ai)
+Get key from: [Cohere Dashboard](https://dashboard.cohere.com)
 
-### Amazon (Nova)
+### HuggingFace Inference
 ```
-LLM_API_KEY=your_amazon_api_key
-LLM_MODEL=amazon/nova-premier-v1
+LLM_API_KEY=hf_your_token
+LLM_MODEL=huggingface/deepseek-ai/DeepSeek-R1
 ```
-Models: `amazon/nova-premier-v1` · `amazon/nova-pro-v1` · `amazon/nova-lite-v1`
+Get key from: [HuggingFace Tokens](https://huggingface.co/settings/tokens)
 
 ### OpenRouter (300+ models via single API key)
 ```
@@ -272,18 +254,22 @@ LLM_MODEL=openrouter/anthropic/claude-sonnet-4-6
 ```
 With OpenRouter, you can access **every model above** with a single API key! Just prefix with `openrouter/`:
 - `openrouter/anthropic/claude-sonnet-4-6` — Anthropic Claude
-- `openrouter/openai/gpt-5.4` — OpenAI (1M context)
-- `openrouter/deepseek/deepseek-v3.2` — DeepSeek V3.2
+- `openrouter/openai/gpt-5.4` — OpenAI
+- `openrouter/deepseek/deepseek-v3.2` — DeepSeek
 - `openrouter/google/gemini-2.5-flash` — Google Gemini
-- `openrouter/qwen/qwen3.6-plus-preview:free` — Qwen (free!)
-- `openrouter/x-ai/grok-4.20-beta` — xAI Grok
 - `openrouter/meta-llama/llama-3.3-70b-instruct:free` — Llama (free!)
-- `openrouter/mistralai/mistral-large-2512` — Mistral Large
 - `openrouter/moonshotai/kimi-k2.5` — Moonshot Kimi
 - `openrouter/z-ai/glm-5-turbo` — Z.ai GLM
 
 Get key from: [OpenRouter.ai](https://openrouter.ai) · [Full model list](https://openrouter.ai/models)
 
+### Kilo Gateway
+```
+LLM_API_KEY=your_kilocode_api_key
+LLM_MODEL=kilocode/anthropic/claude-opus-4.6
+```
+Get key from: [Kilo.ai](https://kilo.ai)
+
 ### Any Other Provider
 HuggingClaw supports **any LLM provider** that OpenClaw supports. Just use:
 ```
@@ -292,6 +278,8 @@ LLM_MODEL=provider/model-name
 ```
 The provider prefix is auto-detected and mapped to the appropriate environment variable.
 
+Full provider list: [OpenClaw Model Providers](https://docs.openclaw.ai/concepts/model-providers) · [OpenCode Providers](https://opencode.ai/docs/providers)
+
 ---
 
 ## 📱 Telegram Setup

start.sh

@@ -43,38 +43,45 @@ fi
 LLM_PROVIDER=$(echo "$LLM_MODEL" | cut -d'/' -f1)
 
 # Map provider prefix to the correct API key environment variable
-# Based on actual OpenRouter model IDs: https://openrouter.ai/api/v1/models
+# Based on OpenClaw provider system: /usr/local/lib/node_modules/openclaw/docs/concepts/model-providers.md
+# Note: OpenClaw normalizes some prefixes (z-ai → zai, z.ai → zai, etc.)
 case "$LLM_PROVIDER" in
-  openrouter)       export OPENROUTER_API_KEY="$LLM_API_KEY" ;;
-  anthropic)        export ANTHROPIC_API_KEY="$LLM_API_KEY" ;;
-  openai)           export OPENAI_API_KEY="$LLM_API_KEY" ;;
-  google)           export GOOGLE_API_KEY="$LLM_API_KEY" ;;
-  deepseek)         export DEEPSEEK_API_KEY="$LLM_API_KEY" ;;
-  mistralai)        export MISTRAL_API_KEY="$LLM_API_KEY" ;;
-  qwen)             export QWEN_API_KEY="$LLM_API_KEY" ;;
-  x-ai)             export XAI_API_KEY="$LLM_API_KEY" ;;
-  meta-llama)       export META_API_KEY="$LLM_API_KEY" ;;
-  minimax)          export MINIMAX_API_KEY="$LLM_API_KEY" ;;
-  z-ai)             export ZAI_API_KEY="$LLM_API_KEY" ;;
-  moonshotai)       export MOONSHOT_API_KEY="$LLM_API_KEY" ;;
-  nvidia)           export NVIDIA_API_KEY="$LLM_API_KEY" ;;
-  cohere)           export COHERE_API_KEY="$LLM_API_KEY" ;;
-  perplexity)       export PERPLEXITY_API_KEY="$LLM_API_KEY" ;;
-  bytedance-seed)   export BYTEDANCE_API_KEY="$LLM_API_KEY" ;;
-  xiaomi)           export XIAOMI_API_KEY="$LLM_API_KEY" ;;
-  amazon)           export AMAZON_API_KEY="$LLM_API_KEY" ;;
-  reka|rekaai)      export REKA_API_KEY="$LLM_API_KEY" ;;
-  inception)        export INCEPTION_API_KEY="$LLM_API_KEY" ;;
-  kwaipilot)        export KWAIPILOT_API_KEY="$LLM_API_KEY" ;;
-  ai21)             export AI21_API_KEY="$LLM_API_KEY" ;;
-  baidu)            export BAIDU_API_KEY="$LLM_API_KEY" ;;
-  tencent)          export TENCENT_API_KEY="$LLM_API_KEY" ;;
-  stepfun)          export STEPFUN_API_KEY="$LLM_API_KEY" ;;
-  inflection)       export INFLECTION_API_KEY="$LLM_API_KEY" ;;
-  writer)           export WRITER_API_KEY="$LLM_API_KEY" ;;
-  upstage)          export UPSTAGE_API_KEY="$LLM_API_KEY" ;;
+  # ── Core Providers ──
+  anthropic)                    export ANTHROPIC_API_KEY="$LLM_API_KEY" ;;
+  openai|openai-codex)          export OPENAI_API_KEY="$LLM_API_KEY" ;;
+  google|google-vertex)         export GEMINI_API_KEY="$LLM_API_KEY" ;;
+  deepseek)                     export DEEPSEEK_API_KEY="$LLM_API_KEY" ;;
+  # ── OpenCode Providers ──
+  opencode)                     export OPENCODE_API_KEY="$LLM_API_KEY" ;;
+  opencode-go)                  export OPENCODE_API_KEY="$LLM_API_KEY" ;;
+  # ── Gateway/Router Providers ──
+  openrouter)                   export OPENROUTER_API_KEY="$LLM_API_KEY" ;;
+  kilocode)                     export KILOCODE_API_KEY="$LLM_API_KEY" ;;
+  vercel-ai-gateway)            export AI_GATEWAY_API_KEY="$LLM_API_KEY" ;;
+  # ── Chinese/Asian Providers ──
+  zai|z-ai|z.ai|zhipu)          export ZAI_API_KEY="$LLM_API_KEY" ;;
+  moonshot)                     export MOONSHOT_API_KEY="$LLM_API_KEY" ;;
+  kimi-coding)                  export KIMI_API_KEY="$LLM_API_KEY" ;;
+  minimax)                      export MINIMAX_API_KEY="$LLM_API_KEY" ;;
+  qwen|modelstudio)             export MODELSTUDIO_API_KEY="$LLM_API_KEY" ;;
+  xiaomi)                       export XIAOMI_API_KEY="$LLM_API_KEY" ;;
+  volcengine|volcengine-plan)   export VOLCANO_ENGINE_API_KEY="$LLM_API_KEY" ;;
+  byteplus|byteplus-plan)       export BYTEPLUS_API_KEY="$LLM_API_KEY" ;;
+  qianfan)                      export QIANFAN_API_KEY="$LLM_API_KEY" ;;
+  # ── Western Providers ──
+  mistral|mistralai)            export MISTRAL_API_KEY="$LLM_API_KEY" ;;
+  xai|x-ai)                    export XAI_API_KEY="$LLM_API_KEY" ;;
+  nvidia)                       export NVIDIA_API_KEY="$LLM_API_KEY" ;;
+  cohere)                       export COHERE_API_KEY="$LLM_API_KEY" ;;
+  groq)                         export GROQ_API_KEY="$LLM_API_KEY" ;;
+  together)                     export TOGETHER_API_KEY="$LLM_API_KEY" ;;
+  huggingface)                  export HUGGINGFACE_HUB_TOKEN="$LLM_API_KEY" ;;
+  cerebras)                     export CEREBRAS_API_KEY="$LLM_API_KEY" ;;
+  venice)                       export VENICE_API_KEY="$LLM_API_KEY" ;;
+  synthetic)                    export SYNTHETIC_API_KEY="$LLM_API_KEY" ;;
+  github-copilot)               export COPILOT_GITHUB_TOKEN="$LLM_API_KEY" ;;
+  # ── Fallback: Anthropic (default) ──
   *)
-    # Fallback: export as ANTHROPIC (default) and also as generic
     export ANTHROPIC_API_KEY="$LLM_API_KEY"
     ;;
 esac