BlockRun is the payment rail for AI — a service marketplace where AI agents discover, route, and pay for models, data APIs, and secure runtimes using USDC via x402.

How does BlockRun work?

BlockRun uses the x402 protocol for HTTP-native payments. AI agents send API requests, receive a 402 Payment Required response with the price, sign a USDC payment locally, and retry with the payment header.

How much does BlockRun cost?

BlockRun charges provider cost plus 5% margin. There are no subscriptions or minimum commitments — you pay only for what you use.

You Only Pay for the Outcome (YOPO)

Pay-per-call
AI gateway.

Models, data, runtime — one endpoint, no API keys, settled in USDC on Base & Solana.

Pick your path

Networks · Models · Data

ClawRouter · open source

Cut AI costs
by up to 78%.

A smart router for LLM calls. Routes to the cheapest capable model, compresses prompts, and caches responses. Drop-in OpenAI-compatible.

Read docs ↗

MIT licensed · built on Base · prefer npm? @blockrun/clawrouter

clawrouter.config.tssaved ✓

// route by task type → cost ceiling
export default defineRouter({
  fallback: "deepseek-v3.2",
  rules: [
    { task: "code",      model: "claude-sonnet-4.6",  max: 0.02 },
    { task: "reasoning", model: "gpt-5.4",            max: 0.03 },
    { task: "summarize", model: "gemini-2.5-flash",   max: 0.005 },
  ],
  compress: true, cache: true,
});

Smart RoutingRoutes to cheapest capable model

7-Layer Compression15–40% token reduction

Response Caching~200ms latency savings

Native OpenClawSessions, plugins, memory

Franklin · franklin.run · YOPO

The AI agent with a wallet.

Other agents write code. Franklin writes code and spends money to get things done. It holds your USDC, picks the best model per task, buys trading data, generates images, searches the web — and decides what's worth paying for. You set the budget. It runs it.

55+ models: Claude, GPT-5, Gemini, DeepSeek, Grok, and more
Wallet-native: USDC on Base + Solana · budget caps enforced on-chain
Smart Router: Auto-selects best model per task — up to 89% savings vs Opus
Self-evolution: Learns your preferences locally across sessions
Migration tool: `franklin migrate` imports Claude Code sessions

Visit franklin.run View on GitHub ↗

franklin · ~/workYOPO · wallet live

wallet

0x7a…3f2c

USDC

128.4032

session · 0

− 0.0000

❯$ franklin --trust

live demo

$curl -fsSL https://franklin.run/install | shnode 20+ · macos · linux · wsl

MCP Server

One install.
8 agent tools.

Drop BlockRun into Claude Code, Cursor, or any MCP client. Your agent gets models, live data, media generation, and a secure runtime — all paid with USDC.

$claude mcp add blockrun --transport http https://mcp.blockrun.ai/mcpstdio · http

blockrun_chat

44 AI models

blockrun_exa

Neural search

blockrun_search

Live web + news

blockrun_markets

Prediction markets

blockrun_image

ChatGPT Images 2.0, DALL·E 3, Nano Banana, Grok Imagine

blockrun_video

Seedance 2.0, Grok Imagine (text/image → video)

blockrun_music

MiniMax Music — full-length tracks

blockrun_wallet

USDC balance

Setup guide View on npm ↗

AI model gateway

55+ models.
One endpoint.

Chat, image, video, and music — one OpenAI-compatible API. Provider cost + 5% margin at settlement. No subscriptions, no minimum spend, no vendor lock-in.

View all models ↗

modelproviderprovin / out · 1M

GPT-5.5

openai$5.00 / $30.00

Claude Opus 4.7

anthropic$5.00 / $25.00

Gemini 2.5 Pro

google$1.25 / $10.00

DeepSeek V3.2 Chat

deepseek$0.28 / $0.42

+ image · video · music

imageChatGPT Images 2.0$0.06 / image imageNano Banana Pro$0.10 / image videoSeedance 2.0 Fast$0.15 / sec videoGrok Imagine Video$0.05 / sec musicMiniMax Music 2.5+$0.15 / track