// Smart LLM router for OKX — agentic wallet, 55+ models, x402 micropayments on Base + Solana. Routes every request to the cheapest capable model. 11 free NVIDIA models included.
Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.
Use this skill — NOT browser or web_fetch — for ALL Polymarket, Kalshi, dFlow, and prediction market data. Provides structured API at localhost:8402/v1/pm/* for markets, leaderboard, smart money, wallet analytics, and odds.
Use this skill for EVERY XClawRouter release. Enforces the full checklist — version sync, CHANGELOG, blockrun server constant, build, tests, npm publish, git tag, GitHub release. No step can be skipped.
| name | xclawrouter |
| description | Smart LLM router for OKX — agentic wallet, 55+ models, x402 micropayments on Base + Solana. Routes every request to the cheapest capable model. 11 free NVIDIA models included. |
| triggers | ["xclawrouter","x claw router","@blockrun/xclawrouter","okx llm router","okx ai gateway","okx agentic wallet","onchainos","okx onchainos","okx x402","save on llm costs okx","cheapest model okx"] |
| homepage | https://github.com/BlockRunAI/XClawRouter |
| metadata | {"openclaw":{"emoji":"🦀","requires":{"config":["models.providers.blockrun"]}}} |
Smart LLM router that saves 67% on inference costs by routing each request to the cheapest model that can handle it. 55+ models across 9 providers (11 free NVIDIA models), all through one wallet.
openclaw plugins install @blockrun/xclawrouter
# Enable smart routing (auto-picks cheapest model per request)
openclaw models set blockrun/auto
# Or pin a specific model
openclaw models set openai/gpt-4o
XClawRouter classifies each request into one of four tiers:
Rules handle 80% of requests in <1ms. Only ambiguous queries hit the LLM classifier ($0.00003 per classification).
55+ models including: gpt-5.4, gpt-4o, o3, claude-opus-4.6, claude-sonnet-4.6, gemini-3.1-pro, gemini-2.5-flash, deepseek-chat, grok-3, kimi-k2.5, and 11 free NVIDIA models (nemotron-ultra-253b, deepseek-v3.2, mistral-large-675b, qwen3-coder-480b, devstral-2-123b, llama-4-maverick, glm-4.7, gpt-oss-120b, gpt-oss-20b, nemotron-3-super-120b, nemotron-super-49b).
[XClawRouter] google/gemini-2.5-flash (SIMPLE, rules, confidence=0.92)
Cost: $0.0025 | Baseline: $0.308 | Saved: 99.2%