For developers
Pay per call. Two ways in.
One endpoint, 117 models, each priced before it runs. ClawRouter, our open-source router, classifies each request locally and sends it to the cheapest model that can complete it.
$ pip install blockrun-llm $ export BLOCKRUN_WALLET_KEY=0x… # signs locally, never sent $ python -c "from blockrun_llm import LLMClient; print(LLMClient().chat('openai/gpt-6-luna', 'Hello!'))" → 402 priced before it runs → 200 settled · Hello! How can I help?
landing · 5.6°Wallet · no account
USDC on Base, Solana or Arc, signed locally, settled in the same request.
Pay from a walletWhat runs it
01 · ClawRouter
The cheapest model that can do the job.
MIT. Classifies each request locally in under a millisecond. The published auto profile saves 84%.
02 · BlockRun MCP
Claude Code, Cursor, OpenClaw, ChatGPT.
Tools for the harnesses people use. Each call is priced before it runs.
03 · SDKs
Python, TypeScript and Go.
blockrun-llm on PyPI, @blockrun/llm on npm, blockrun-llm-go on GitHub. MIT.
04 · Models
Every model, with its per-call price.
Chat, reasoning, coding and vision; image, video, music and speech. Free open-weight models to try without paying.