Blockrun LLM — AI skill for Claude Code
Python SDK for BlockRun — every frontier model, pay-per-call with USDC.
How to install Blockrun LLM
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open BlockRunAI/blockrun-llm and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Blockrun LLM does
Python SDK for BlockRun — every frontier model, pay-per-call with USDC. OpenAI-compatible. Zero rate limits.
Alternatives in AI
- Axonhub — ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs 3.2k ★
- WindsurfAPI — Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A 3k ★
- Image Use — Use your ChatGPT subscription to generate images from the command line — no OPENAI_API_KEY, no gateway, no dae 373 ★
README
BlockRun LLM SDK (Python)
**blockrun-llm** is a Python SDK for accessing 80+ large language models (GPT-5.x, Claude 4.x, Gemini 3.x, DeepSeek, Grok 4.x, GLM, MiniMax, Moonshot and more) plus image / video / music generation, Grok Live Search, prediction-market data (Predexon), Exa neural web search, and Pyth-backed market data. Every call is paid per request — no subscription, no seats, no minimum. Built for AI agents that need to operate autonomously.
**Two ways to pay, same SDK, same catalogue.** Sign up at **[user.blockrun.ai](https://user.blockrun.ai)** for an API key and prepaid credit (top up with a card), or hold USDC in your own wallet and let each request settle itself over x402 — on **Solana or Base**. Every client takes either credential in the same first argument.
🆓 **Includes 8 fully-free NVIDIA-hosted models** — DeepSeek V4 Flash (1M context), Nemotron Nano Omni (vision), Qwen3 Next + Coder, Llama 4 Maverick, Mistral Small 4, plus `gpt-oss-120b/20b` (hidden from `/v1/models` but direct calls still work). Zero USDC, no rate-limit gimmicks. Use `routing_profile="free"` or call any `nvidia/*` model directly.
[](https://pypi.org/project/blockrun-llm/) [](LICENSE)
**BlockRun assumes Claude Code as the agent runtime.**
Supported Chains
| Rail | Network | Payment | Status |
|---|---|---|---|
| API key | none — api.blockrun.ai |
prepaid credit, topped up with a card | ✅ |
| Solana | Solana Mainnet | USDC (SPL), gasless — the facilitator pays the fee | ✅ Recommended for x402 |
| Base | Base Mainnet (Chain ID: 8453) | USDC | ✅ |
| Arc | Circle Arc (Chain ID: 5042) — arc.blockrun.ai |
USDC (Arc's native token), settled by Circle — no gas per call | ✅ |
| Base Testnet | Base Sepolia (Chain ID: 84532) | Testnet USDC | ✅ Development |
**Protocol:** x402 v2 on the wallet rai
Related Skills
ClawRouter Hermes
ClawRouter for Hermes — BlockRun's full LLM catalog incl. Claude, GPT and Grok; x402 USDC micropayments on Bas
X402 Agent Search Examples
CyberWareX: web search, web page reading and token safety checks for AI agents, paid per call in USDC with x40
Awareness SDK
Local-first AI agent memory — one command, 13+ IDEs, works offline. Persistent memory for Claude Code, Cursor,
Radius
AI agents run shell commands on your machine. One hallucination = rm -rf or leaked ~/.ssh. RADIUS intercepts e
Venice Py
Unofficial async-first Python SDK for the Venice.ai API — chat, image, video, music, audio, embeddings, TEE at
Scraper Run
Deterministic extraction engine. Loads a blueprint, executes pagination, handles auth refresh, rate limits, an
Related Agents
Grok Agent 01
ONLY job: find free or freemium AI token/API plans (OpenAI-compatible, Anthropic, Google, open routers, studen
AI Recon
Delegates to this agent when the user wants to map the AI attack surface of an authorized web application befo
Openrouter Agent
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against