@blockrun/clawrouter

v0.12.108

Published

2 days ago

Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.

ClawRouter is an open-source smart LLM router that reduces AI API costs by up to 92%. It analyzes each request across 15 dimensions and routes to the cheapest capable model in under 1ms, entirely locally. ClawRouter is the only LLM router built for autonomous AI agents — it uses wallet signatures for authentication (no API keys) and USDC micropayments via the x402 protocol (no credit cards). 55+ models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. MIT licensed.

Why ClawRouter exists

Every other LLM router was built for human developers — create an account, get an API key, pick a model from a dashboard, pay with a credit card.

Agents can't do any of that.

ClawRouter is built for the agent-first world:

No accounts — a wallet is generated locally, no signup
No API keys — your wallet signature IS authentication
No model selection — 15-dimension scoring picks the right model automatically
No credit cards — agents pay per-request with USDC via x402
No trust required — runs locally, <1ms routing, zero external dependencies

This is the stack that lets agents operate autonomously: x402 + USDC + local routing.

How it compares

| | OpenRouter | LiteLLM | Martian | Portkey | ClawRouter | | ---------------- | ----------------- | ---------------- | ----------------- | ----------------- | ----------------------- | | Models | 200+ | 100+ | Smart routing | Gateway | 55+ | | Routing | Manual selection | Manual selection | Smart (closed) | Observability | Smart (open source) | | Auth | Account + API key | Your API keys | Account + API key | Account + API key | Wallet signature | | Payment | Credit card | BYO keys | Credit card | $49-499/mo | USDC per-request | | Runs locally | No | Yes | No | No | Yes | | Open source | No | Yes | No | Partial | Yes | | Agent-ready | No | No | No | No | Yes |

✓ Open source · ✓ Smart routing · ✓ Runs locally · ✓ Crypto native · ✓ Agent ready

We're the only one that checks all five boxes.

Quick Start

Option A — OpenClaw Agent

OpenClaw is an AI coding agent. If you're using it, ClawRouter installs as a plugin:

curl -fsSL https://blockrun.ai/ClawRouter-update | bash
openclaw gateway restart

Done. Smart routing (blockrun/auto) is now your default model.

Option B — Standalone (continue.dev, Cursor, VS Code, any OpenAI-compatible client)

Using Claude Code? Check out BRCC — it's purpose-built for Claude Code with the same smart routing and x402 payments.

No OpenClaw required. ClawRouter runs as a local proxy on port 8402.

1. Start the proxy

npx @blockrun/clawrouter

2. Fund your wallet Your wallet address is printed on first run. Send a few USDC on Base or Solana — $5 covers thousands of requests.

3. Point your client at http://localhost:8402

Important: apiBase must end with /v1/ (including the trailing slash). Without it, continue.dev constructs the URL as /chat/completions instead of /v1/chat/completions, and the proxy returns 404.

models:
  - name: ClawRouter Auto
    provider: openai
    model: blockrun/auto
    apiBase: http://localhost:8402/v1/
    apiKey: x402
    roles:
      - chat
      - edit
      - apply

To pin a specific model, replace blockrun/auto with any model from blockrun.ai/models, e.g. anthropic/claude-opus-4.6, xai/grok-4-0709.

Both provider: openai and provider: clawrouter work — just make sure apiBase ends with /v1/.

{
  "models": [
    {
      "title": "ClawRouter Auto",
      "provider": "openai",
      "model": "blockrun/auto",
      "apiBase": "http://localhost:8402/v1/",
      "apiKey": "x402"
    }
  ]
}

Set base URL to http://localhost:8402, API key to x402, model to blockrun/auto.

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8402", api_key="x402")
response = client.chat.completions.create(model="blockrun/auto", messages=[...])

Routing Profiles

Choose your routing strategy with /model <profile>:

| Profile | Strategy | Savings | Best For | | ---------------- | ------------------ | ------- | ---------------- | | /model auto | Balanced (default) | 74-100% | General use | | /model eco | Cheapest possible | 95-100% | Maximum savings | | /model premium | Best quality | 0% | Mission-critical |

Shortcuts: /model grok, /model br-sonnet, /model gpt5, /model o3

How It Works

100% local routing. <1ms latency. Zero external API calls.

Request → Weighted Scorer (15 dimensions) → Tier → Best Model → Response

| Tier | ECO Model | AUTO Model | PREMIUM Model | | --------- | ----------------------------------- | ------------------------------------- | ---------------------------- | | SIMPLE | nvidia/gpt-oss-120b (FREE) | gemini-2.5-flash ($0.30/$2.50) | kimi-k2.5 | | MEDIUM | gemini-3.1-flash-lite ($0.25/$1.50) | kimi-k2.5 ($0.60/$3.00) | gpt-5.3-codex ($1.75/$14.00) | | COMPLEX | gemini-3.1-flash-lite ($0.25/$1.50) | gemini-3.1-pro ($2/$12) | claude-opus-4.6 ($5/$25) | | REASONING | grok-4-1-fast ($0.20/$0.50) | grok-4-1-fast-reasoning ($0.20/$0.50) | claude-sonnet-4.6 ($3/$15) |

Blended average: $2.05/M vs $25/M for Claude Opus = 92% savings

Image Generation

Generate images directly from chat with /imagegen:

/imagegen a dog dancing on the beach
/imagegen --model dall-e-3 a futuristic city at sunset
/imagegen --model banana-pro --size 2048x2048 mountain landscape

| Model | Provider | Price | Max Size | | ------------- | --------------------- | ----------- | --------- | | nano-banana | Google Gemini Flash | $0.05/image | 1024x1024 | | banana-pro | Google Gemini Pro | $0.10/image | 4096x4096 | | dall-e-3 | OpenAI DALL-E 3 | $0.04/image | 1792x1024 | | gpt-image | OpenAI GPT Image 1 | $0.02/image | 1536x1024 | | flux | Black Forest Flux 1.1 | $0.04/image | 1024x1024 |

Image Editing (img2img)

Edit existing images with /img2img:

/img2img --image ~/photo.png change the background to a starry sky
/img2img --image ./cat.jpg --mask ./mask.png remove the background

| Option | Required | Description | | ----------------- | -------- | ------------------------------------- | | --image <path> | Yes | Local image file path (supports ~/) | | --mask <path> | No | Mask image (white = area to edit) | | --model <model> | No | Model to use (default: gpt-image-1) | | --size <WxH> | No | Output size (default: 1024x1024) |

API endpoint: POST http://localhost:8402/v1/images/image2image — see full docs.

Models & Pricing

55+ models across 9 providers, one wallet. Starting at $0.0002/request.

💡 "Cost per request" = estimated cost for a typical chat message (~500 input + 500 output tokens).

Budget Models (under $0.001/request)

| Model | ----------------------------- | nvidia/gpt-oss-120b | nvidia/gpt-oss-20b | nvidia/nemotron-ultra-253b | nvidia/nemotron-3-super-120b | nvidia/nemotron-super-49b | nvidia/deepseek-v3.2 | nvidia/mistral-large-3-675b | nvidia/qwen3-coder-480b | nvidia/devstral-2-123b | nvidia/glm-4.7 | nvidia/llama-4-maverick | openai/gpt-5-nano | openai/gpt-4.1-nano | google/gemini-2.5-flash-lite | | openai/gpt-4o-mini | xai/grok-4-fast | xai/grok-4-fast-reasoning | xai/grok-4-1-fast | xai/grok-4-1-fast-reasoning | | xai/grok-4-0709 | openai/gpt-5-mini | deepseek/deepseek-chat | deepseek/deepseek-reasoner | | xai/grok-3-mini | minimax/minimax-m2.7 | minimax/minimax-m2.5 | google/gemini-2.5-flash | openai/gpt-4.1-mini | google/gemini-3-flash-preview | | nvidia/kimi-k2.5 | moonshot/kimi-k2.5 | Input $/M | Output $/M | ~$/request | Context | Features | | --------: | ---------: | ---------: | ------- | --------------------------------- | | FREE | FREE | $0 | 128K | | | FREE | FREE | $0 | 128K | | | FREE | FREE | $0 | 131K | reasoning | | FREE | FREE | $0 | 131K | reasoning | | FREE | FREE | $0 | 131K | reasoning | | FREE | FREE | $0 | 131K | reasoning | | FREE | FREE | $0 | 131K | reasoning | | FREE | FREE | $0 | 131K | | | FREE | FREE | $0 | 131K | | | FREE | FREE | $0 | 131K | reasoning | | FREE | FREE | $0 | 131K | reasoning | | $0.05 | $0.40 | $0.0002 | 128K | tools | | $0.10 | $0.40 | $0.0003 | 128K | tools | $0.10 | $0.40 | $0.0003 | 1M | tools | | $0.15 | $0.60 | $0.0004 | 128K | tools | | $0.20 | $0.50 | $0.0004 | 131K | tools | | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools | | $0.20 | $0.50 | $0.0004 | 131K | tools | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools | | $0.20 | $1.50 | $0.0009 | 131K | reasoning, tools | | $0.25 | $2.00 | $0.0011 | 200K | tools | | $0.28 | $0.42 | $0.0004 | 128K | tools | $0.28 | $0.42 | $0.0004 | 128K | reasoning, tools | | $0.30 | $0.50 | $0.0004 | 131K | tools | | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools | | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools | | $0.30 | $2.50 | $0.0014 | 1M | vision, tools | | $0.40 | $1.60 | $0.0010 | 128K | tools | $0.50 | $3.00 | $0.0018 | 1M | vision | | $0.55 | $2.50 | $0.0015 | 262K | tools | | $0.60 | $3.00 | $0.0018 | 262K | reasoning, vision, agentic, tools |

Mid-Range Models ($0.001–$0.01/request)

| Model | Input $/M | Output $/M | ~$/request | Context | Features | | --------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- | | anthropic/claude-haiku-4.5 | $1.00 | $5.00 | $0.0030 | 200K | vision, agentic, tools | | zai/glm-5 | $1.00 | $3.20 | $0.0021 | 200K | tools | | openai/o1-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools | | openai/o3-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools | | openai/o4-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools | | zai/glm-5-turbo | $1.20 | $4.00 | $0.0026 | 200K | tools | | google/gemini-2.5-pro | $1.25 | $10.00 | $0.0056 | 1M | reasoning, vision, tools | | openai/gpt-5.2 | $1.75 | $14.00 | $0.0079 | 400K | reasoning, vision, agentic, tools | | openai/gpt-5.3 | $1.75 | $14.00 | $0.0079 | 128K | reasoning, vision, agentic, tools | | openai/gpt-5.3-codex | $1.75 | $14.00 | $0.0079 | 400K | agentic, tools | | openai/gpt-4.1 | $2.00 | $8.00 | $0.0050 | 128K | vision, tools | | openai/o3 | $2.00 | $8.00 | $0.0050 | 200K | reasoning, tools | | google/gemini-3-pro-preview | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools | | google/gemini-3.1-pro | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools | | xai/grok-2-vision | $2.00 | $10.00 | $0.0060 | 131K | vision, tools | | openai/gpt-4o | $2.50 | $10.00 | $0.0063 | 128K | vision, agentic, tools | | openai/gpt-5.4 | $2.50 | $15.00 | $0.0088 | 400K | reasoning, vision, agentic, tools |

Premium Models ($0.01+/request)

Free tier: 11 models cost nothing — /model free points to nemotron-ultra-253b, or pick any free model directly (e.g., /model nemotron, /model deepseek-free, /model devstral). Best value: gpt-5-nano and gemini-2.5-flash-lite deliver strong results at ~$0.0003/request.

Payment

No account. No API key. Payment IS authentication via x402.

Request → 402 (price: $0.003) → wallet signs USDC → retry → response

USDC stays in your wallet until spent — non-custodial. Price is visible in the 402 header before signing.

Dual-chain support: Pay with USDC on Base (EVM) or USDC on Solana. Both wallets are derived from a single BIP-39 mnemonic on first run.

/wallet              # Check balance and address (both chains)
/wallet export       # Export mnemonic + keys for backup
/wallet recover      # Restore wallet from mnemonic on a new machine
/wallet solana       # Switch to Solana USDC payments
/wallet base         # Switch back to Base (EVM) USDC payments
/chain solana        # Alias for /wallet solana
/stats               # View usage and savings
/stats clear         # Reset usage statistics
/exclude             # Show excluded models
/exclude add <model> # Block a model from routing (aliases work: "grok-4", "free")
/exclude remove <model> # Unblock a model
/exclude clear       # Remove all exclusions

Fund your wallet:

Base (EVM): Send USDC on Base to your EVM address
Solana: Send USDC on Solana to your Solana address
Coinbase/CEX: Withdraw USDC to either network
Credit card: Reach out to @bc1max on Telegram

Screenshots

Configuration

For basic usage, no configuration needed. For advanced options:

| Variable | Default | Description | | --------------------------- | ------------------------------------- | ----------------------- | | BLOCKRUN_WALLET_KEY | auto-generated | Your wallet private key | | BLOCKRUN_PROXY_PORT | 8402 | Local proxy port | | CLAWROUTER_DISABLED | false | Disable smart routing | | CLAWROUTER_SOLANA_RPC_URL | https://api.mainnet-beta.solana.com | Solana RPC endpoint |

Full reference: docs/configuration.md

Model Exclusion

Block specific models from being routed to. Useful if a model doesn't follow your agent instructions or you want to control costs.

/exclude add nvidia/gpt-oss-120b   # Block the free model
/exclude add grok-4                # Aliases work — blocks all grok-4 variants
/exclude add gpt-5.4               # Skip expensive models
/exclude                           # Show current exclusions
/exclude remove grok-4             # Unblock a model
/exclude clear                     # Remove all exclusions

Exclusions persist across restarts (~/.openclaw/blockrun/exclude-models.json). If all models in a tier are excluded, the safety net ignores the filter so routing never breaks.

Troubleshooting

When things go wrong, run the doctor:

npx @blockrun/clawrouter doctor

This collects diagnostics and sends them to Claude Sonnet for AI-powered analysis:

🩺 BlockRun Doctor v0.12.24

System
  ✓ OS: darwin arm64
  ✓ Node: v20.11.0

Wallet
  ✓ Address: 0x1234...abcd
  ✓ Balance: $12.50

Network
  ✓ BlockRun API: reachable (142ms)
  ✗ Local proxy: not running on :8402

📤 Sending to Claude Sonnet 4.6 (~$0.003)...

🤖 AI Analysis:
The local proxy isn't running. Run `openclaw gateway restart` to fix.

Use Opus for complex issues:

npx @blockrun/clawrouter doctor opus

Ask a specific question:

npx @blockrun/clawrouter doctor "why is my request failing?"
npx @blockrun/clawrouter doctor opus "深度分析我的配置"

Cost: Sonnet ~$0.003 (default) | Opus ~$0.01

Development

git clone https://github.com/BlockRunAI/ClawRouter.git
cd ClawRouter
npm install
npm run build
npm test

Support

| Channel | Link | | --------------------- | ------------------------------------------------------------------ | | 📅 Schedule Demo | calendly.com/vickyfu9/30min | | 💬 Community Telegram | t.me/blockrunAI | | 🐦 X / Twitter | x.com/blockrunai | | 📱 Founder Telegram | @bc1max | | ✉️ Email | [email protected] |

From the BlockRun Ecosystem

⚡ ClawRouter

The LLM router built for autonomous agents

You're here. 55+ models, local smart routing, x402 USDC payments — the only stack that lets agents operate independently.

curl -fsSL https://blockrun.ai/ClawRouter-update | bash

🤖 BRCC

BlockRun for Claude Code

Run Claude Code with 50+ models, no rate limits, no Anthropic account, no phone verification. Pay per request with USDC — your wallet is your identity.

curl -fsSL https://blockrun.ai/brcc-install | bash

More Resources

| Resource | Description | | ------------------------------------------------------ | ------------------------ | | Documentation | Full docs | | Model Pricing | All models & prices | | Image Generation & Editing | API examples, 5 models | | Routing Profiles | ECO/AUTO/PREMIUM details | | Architecture | Technical deep dive | | Configuration | Environment variables | | Troubleshooting | Common issues |

Blog

| Article | Topic | | -------------------------------------------------------------------------------------------------- | ------------------------------------------------------- | | 11 Free AI Models, Zero Cost | How BlockRun gives developers top-tier LLMs for nothing | | ClawRouter Cuts LLM API Costs 500× | Deep dive into cost savings | | ClawRouter vs OpenRouter | Head-to-head comparison | | Smart LLM Router: 14-Dimension Classifier | How the routing engine works | | LLM Router Benchmark: 46 Models, Sub-1ms | Performance benchmarks | | Anthropic Cost Savings | Reducing Claude API spend |

Frequently Asked Questions

What is ClawRouter?

ClawRouter is an open-source (MIT licensed) smart LLM router built for autonomous AI agents. It analyzes each request across 15 dimensions and routes to the cheapest capable model in under 1ms, entirely locally — no external API calls needed for routing decisions.

How much can ClawRouter save on LLM costs?

ClawRouter's blended average cost is $2.05 per million tokens compared to $25/M for Claude Opus, representing 92% savings. Actual savings depend on your workload — simple queries are routed to free models ($0/request), while complex tasks get premium models.

How does ClawRouter compare to OpenRouter?

ClawRouter is open source and runs locally. It uses wallet-based authentication (no API keys) and USDC per-request payments (no credit cards or subscriptions). OpenRouter requires an account, API key, and credit card. ClawRouter also features smart routing — it automatically picks the best model for each request, while OpenRouter requires manual model selection.

How does ClawRouter compare to LiteLLM?

Both are open source and run locally. But ClawRouter adds smart routing (automatic model selection), wallet-based auth, and USDC payments. LiteLLM requires you to bring your own API keys and manually choose models.

What agents does ClawRouter work with?

ClawRouter works with any tool that makes OpenAI-compatible API calls — point it at http://localhost:8402. This includes continue.dev, Cursor, VS Code extensions, ElizaOS, and custom agents. It also integrates as a plugin with OpenClaw (an AI coding agent), which enables additional features like slash commands and usage reports.

Is ClawRouter free?

ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it — and 11 models (DeepSeek V3.2, Nemotron Ultra 253B, Mistral Large 675B, Llama 4 Maverick, and more) are completely free. Use /model free for Nemotron Ultra 253B, or pick any free model by name.

MIT License · BlockRun — Agent-native AI infrastructure

⭐ If ClawRouter powers your agents, consider starring the repo!