@blockrun/clawrouter
Advanced tools
Smart LLM router โ save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.
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.
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 โ 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.
Every other LLM router was built for human developers โ 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:
This is the stack that lets agents operate autonomously: x402 + USDC + local routing.
| 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 |
โ Open source ยท โ Smart routing ยท โ Runs locally ยท โ Crypto native ยท โ Agent ready
We're the only one that checks all five boxes.
# 1. Install with smart routing enabled
curl -fsSL https://blockrun.ai/ClawRouter-update | bash
openclaw gateway restart
# 2. Fund your wallet with USDC on Base or Solana (address printed on install)
# $5 is enough for thousands of requests
Done. Smart routing (blockrun/auto) is now your default model.
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
100% local routing. <1ms latency. Zero external API calls.
Request โ Weighted Scorer (15 dimensions) โ Tier โ Best Model โ 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
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 |
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 โ see full docs.
55+ models across 9 providers, one wallet. Starting at $0.0002/request.
๐ก "Cost per request" = estimated cost for a typical chat message (~500 input + 500 output tokens).
| 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 |
| 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 |
| 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 NVIDIA models cost nothing โ
/model freepoints to nemotron-ultra-253b, or pick any free model directly (e.g.,/model nemotron,/model deepseek-free,/model devstral). Best value:gpt-5-nanoandgemini-2.5-flash-litedeliver strong results at ~$0.0003/request.
No account. No API key. Payment IS authentication via x402.
Request โ 402 (price: $0.003) โ wallet signs USDC โ retry โ response
USDC stays in your wallet until spent โ 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:
Smart Routing in Action
|
Telegram Integration
|
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
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 โ 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.
When things go wrong, run the doctor:
npx @blockrun/clawrouter doctor
This collects diagnostics and sends them to Claude Sonnet for AI-powered analysis:
๐ฉบ BlockRun Doctor v0.12.24
System
โ OS: darwin arm64
โ Node: v20.11.0
Wallet
โ Address: 0x1234...abcd
โ Balance: $12.50
Network
โ BlockRun API: reachable (142ms)
โ Local proxy: not running on :8402
๐ค Sending to Claude Sonnet 4.6 (~$0.003)...
๐ค 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 "ๆทฑๅบฆๅๆๆ็้
็ฝฎ"
Cost: Sonnet ~$0.003 (default) | Opus ~$0.01
git clone https://github.com/BlockRunAI/ClawRouter.git
cd ClawRouter
npm install
npm run build
npm test
| Channel | Link |
|---|---|
| ๐ Schedule Demo | calendly.com/vickyfu9/30min |
| ๐ฌ Community Telegram | t.me/blockrunAI |
| ๐ฆ X / Twitter | x.com/blockrunai |
| ๐ฑ Founder Telegram | @bc1max |
| โ๏ธ Email | vicky@blockrun.ai |
โก ClawRouterThe LLM router built for autonomous agents You're here. 55+ models, local smart routing, x402 USDC payments โ the only stack that lets agents operate independently.
|
๐ฆ SocialClawIntelligence-as-a-function for X/Twitter The first X analytics an agent can call. One function call = one intelligence report. $0.08, not $49/month. No dashboard, no login, no subscription.
|
| 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 |
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 โ no external API calls needed for routing decisions.
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 โ simple queries are routed to budget models (as low as $0/request with NVIDIA free tier), while complex tasks get premium models.
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 โ it automatically picks the best model for each request, while OpenRouter requires manual model selection.
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.
ClawRouter integrates with OpenClaw (Claude Code), ElizaOS, and any agent that makes OpenAI-compatible API calls. It runs as a local proxy on port 8402.
ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it โ and 11 NVIDIA 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 ยท BlockRun โ Agent-native AI infrastructure
โญ If ClawRouter powers your agents, consider starring the repo!
FAQs
Smart LLM router โ save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.
The npm package @blockrun/clawrouter receives a total of 3,188 weekly downloads. As such, @blockrun/clawrouter popularity was classified as popular.
We found that @blockrun/clawrouter demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago.ย It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
TeamPCP is partnering with ransomware group Vect to turn open source supply chain attacks on tools like Trivy and LiteLLM into large-scale ransomware operations.
Security News
/Research
Widespread GitHub phishing campaign uses fake Visual Studio Code security alerts in Discussions to trick developers into visiting malicious website.
Security News
Five malicious npm packages typosquatting crypto libraries steal private keys via Telegram, targeting Solana and Ethereum developers, with active C2 infrastructure.
