ClawRouter Banner

The LLM router built for autonomous agents

Agents can't sign up for accounts. Agents can't enter credit cards.
Agents can only sign transactions.

ClawRouter is the only LLM router that lets agents operate independently.

[![npm version](https://img.shields.io/npm/v/@blockrun/clawrouter.svg?style=flat-square&color=cb3837)](https://npmjs.com/package/@blockrun/clawrouter) [![npm downloads](https://img.shields.io/npm/dm/@blockrun/clawrouter.svg?style=flat-square&color=blue)](https://npmjs.com/package/@blockrun/clawrouter) [![GitHub stars](https://img.shields.io/github/stars/BlockRunAI/ClawRouter?style=flat-square)](https://github.com/BlockRunAI/ClawRouter) [![CI](https://img.shields.io/github/actions/workflow/status/BlockRunAI/ClawRouter/ci.yml?style=flat-square&label=CI)](https://github.com/BlockRunAI/ClawRouter/actions) [![TypeScript](https://img.shields.io/badge/TypeScript-5.7-3178c6?style=flat-square&logo=typescript&logoColor=white)](https://typescriptlang.org) [![License: MIT](https://img.shields.io/badge/License-MIT-green?style=flat-square)](LICENSE) [![USDC Hackathon Winner](https://img.shields.io/badge/🏆_USDC_Hackathon-Agentic_Commerce_Winner-gold?style=flat-square)](https://x.com/USDC/status/2021625822294216977) [![x402 Protocol](https://img.shields.io/badge/x402-Micropayments-purple?style=flat-square)](https://x402.org) [![Base Network](https://img.shields.io/badge/Base-USDC-0052FF?style=flat-square&logo=coinbase&logoColor=white)](https://base.org) [![Solana](https://img.shields.io/badge/Solana-USDC-9945FF?style=flat-square&logo=solana&logoColor=white)](https://solana.com) [![OpenClaw Plugin](https://img.shields.io/badge/OpenClaw-Plugin-orange?style=flat-square)](https://openclaw.ai) [![Telegram](https://img.shields.io/badge/Telegram-Community-26A5E4?style=flat-square&logo=telegram)](https://t.me/blockrunAI)

> **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](https://x402.org) - **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](https://openclaw.ai) is an AI coding agent. If you're using it, ClawRouter installs as a plugin: ```bash 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](https://github.com/BlockRunAI/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** ```bash 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`**

continue.dev — ~/.continue/config.yaml

> **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. ```yaml 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](https://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/`.

Legacy JSON format (~/.continue/config.json)

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

Cursor — Settings → Models → OpenAI-compatible

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

Any OpenAI SDK

```python 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 | 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 ` | Yes | Local image file path (supports `~/`) | | `--mask ` | No | Mask image (white = area to edit) | | `--model ` | No | Model to use (default: `gpt-image-1`) | | `--size ` | No | Output size (default: `1024x1024`) | **API endpoint:** `POST http://localhost:8402/v1/images/image2image` — see [full docs](docs/image-generation.md#post-v1imagesimage2image). --- ## 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 | Input $/M | Output $/M | ~$/request | Context | Features | | ----------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- | | nvidia/gpt-oss-120b | **FREE** | **FREE** | **$0** | 128K | | | nvidia/gpt-oss-20b | **FREE** | **FREE** | **$0** | 128K | | | nvidia/nemotron-ultra-253b | **FREE** | **FREE** | **$0** | 131K | reasoning | | nvidia/nemotron-3-super-120b | **FREE** | **FREE** | **$0** | 131K | reasoning | | nvidia/nemotron-super-49b | **FREE** | **FREE** | **$0** | 131K | reasoning | | nvidia/deepseek-v3.2 | **FREE** | **FREE** | **$0** | 131K | reasoning | | nvidia/mistral-large-3-675b | **FREE** | **FREE** | **$0** | 131K | reasoning | | nvidia/qwen3-coder-480b | **FREE** | **FREE** | **$0** | 131K | | | nvidia/devstral-2-123b | **FREE** | **FREE** | **$0** | 131K | | | nvidia/glm-4.7 | **FREE** | **FREE** | **$0** | 131K | reasoning | | nvidia/llama-4-maverick | **FREE** | **FREE** | **$0** | 131K | reasoning | | openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools | | openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools | | google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools | | openai/gpt-4o-mini | $0.15 | $0.60 | $0.0004 | 128K | tools | | xai/grok-4-fast | $0.20 | $0.50 | $0.0004 | 131K | tools | | xai/grok-4-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools | | xai/grok-4-1-fast | $0.20 | $0.50 | $0.0004 | 131K | tools | | xai/grok-4-1-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools | | xai/grok-4-0709 | $0.20 | $1.50 | $0.0009 | 131K | reasoning, tools | | openai/gpt-5-mini | $0.25 | $2.00 | $0.0011 | 200K | tools | | deepseek/deepseek-chat | $0.28 | $0.42 | $0.0004 | 128K | tools | | deepseek/deepseek-reasoner | $0.28 | $0.42 | $0.0004 | 128K | reasoning, tools | | xai/grok-3-mini | $0.30 | $0.50 | $0.0004 | 131K | tools | | minimax/minimax-m2.7 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools | | minimax/minimax-m2.5 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools | | google/gemini-2.5-flash | $0.30 | $2.50 | $0.0014 | 1M | vision, tools | | openai/gpt-4.1-mini | $0.40 | $1.60 | $0.0010 | 128K | tools | | google/gemini-3-flash-preview | $0.50 | $3.00 | $0.0018 | 1M | vision | | nvidia/kimi-k2.5 | $0.55 | $2.50 | $0.0015 | 262K | tools | | moonshot/kimi-k2.5 | $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) | Model | Input $/M | Output $/M | ~$/request | Context | Features | | --------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- | | anthropic/claude-sonnet-4.6 | $3.00 | $15.00 | $0.0090 | 200K | reasoning, vision, agentic, tools | | xai/grok-3 | $3.00 | $15.00 | $0.0090 | 131K | reasoning, tools | | anthropic/claude-opus-4.6 | $5.00 | $25.00 | $0.0150 | 200K | reasoning, vision, agentic, tools | | openai/o1 | $15.00 | $60.00 | $0.0375 | 200K | reasoning, tools | | openai/gpt-5.2-pro | $21.00 | $168.00 | $0.0945 | 400K | reasoning, tools | | openai/gpt-5.4-pro | $30.00 | $180.00 | $0.1050 | 400K | reasoning, tools | > **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](https://x402.org). ``` 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. ```bash /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 # Block a model from routing (aliases work: "grok-4", "free") /exclude remove # 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](https://t.me/bc1max) --- ## Screenshots

Smart Routing in Action

ClawRouter savings

ClawRouter savings

Telegram Integration

--- ## 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](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. ```bash /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:** ```bash 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:** ```bash npx @blockrun/clawrouter doctor opus ``` **Ask a specific question:** ```bash 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 ```bash 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](https://calendly.com/vickyfu9/30min) | | 💬 Community Telegram | [t.me/blockrunAI](https://t.me/blockrunAI) | | 🐦 X / Twitter | [x.com/blockrunai](https://x.com/blockrunai) | | 📱 Founder Telegram | [@bc1max](https://t.me/bc1max) | | ✉️ Email | vicky@blockrun.ai | --- ## 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](https://github.com/BlockRunAI/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` [![GitHub](https://img.shields.io/github/stars/BlockRunAI/brcc?style=flat-square)](https://github.com/BlockRunAI/brcc)

--- ## More Resources | Resource | Description | | ------------------------------------------------------ | ------------------------ | | [Documentation](https://blockrun.ai/docs) | Full docs | | [Model Pricing](https://blockrun.ai/models) | All models & prices | | [Image Generation & Editing](docs/image-generation.md) | API examples, 5 models | | [Routing Profiles](docs/routing-profiles.md) | ECO/AUTO/PREMIUM details | | [Architecture](docs/architecture.md) | Technical deep dive | | [Configuration](docs/configuration.md) | Environment variables | | [Troubleshooting](docs/troubleshooting.md) | Common issues | ### Blog | Article | Topic | | -------------------------------------------------------------------------------------------------- | ------------------------------------------------------- | | [11 Free AI Models, Zero Cost](docs/11-free-ai-models-zero-cost-blockrun.md) | How BlockRun gives developers top-tier LLMs for nothing | | [ClawRouter Cuts LLM API Costs 500×](docs/clawrouter-cuts-llm-api-costs-500x.md) | Deep dive into cost savings | | [ClawRouter vs OpenRouter](docs/clawrouter-vs-openrouter-llm-routing-comparison.md) | Head-to-head comparison | | [Smart LLM Router: 14-Dimension Classifier](docs/smart-llm-router-14-dimension-classifier.md) | How the routing engine works | | [LLM Router Benchmark: 46 Models, Sub-1ms](docs/llm-router-benchmark-46-models-sub-1ms-routing.md) | Performance benchmarks | | [Anthropic Cost Savings](docs/anthropic-cost-savings.md) | 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](https://openclaw.ai) (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](https://blockrun.ai) — Agent-native AI infrastructure ⭐ If ClawRouter powers your agents, consider starring the repo!