For developers
Pay per call. Two ways in.
One endpoint, 124 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.
Everything for developers
Models
- Chat96 frontier LLMs, one OpenAI-compatible API
- ReasoningExtended-thinking models — Opus, o-series, DeepSeek, GLM
- CodingThe models the agent harnesses ship with
- VisionImage and video input, text out
- Free9 open-weight models — no card, no signup
- ImageGPT Image, Nano Banana, Seedream, Grok Imagine
- VideoSeedance 2.5, Grok Imagine Video
- MusicFull tracks from a prompt — MiniMax Music
- SpeechElevenLabs v3 / Flash, Seed Audio — text to voice
Capabilities
- DecisionsUp to 1,000 typed judgments in one call
- ExaNeural web search with grounded answers
- Trading MarketsStocks · crypto · FX · commodities
- PredexonPrediction markets — Polymarket, Kalshi, Limitless
- ModalSandboxed code runtime for agents
- Multi-chain RPCJSON-RPC on 40 chains
- 0x SwapDEX aggregation — Permit2 + Gasless V2
- Phone & VoiceOutbound AI calls, dedicated US/CA numbers
- ElevenLabsText-to-speech and sound effects
- Seedance VideoVideo generation + character enrollment
Open-source router
- ClawRouterOpen-source LLM router — runs on your side, not ours
- For DeepSeek HarnessA stronger model reads the dangerous command before it runs.
- For HermesOne provider block replaces an account at every lab.
- For OpenAI CodexCodex only speaks the Responses API. This translates it.