Do you train on my prompts?

No. We forward your prompt only to the AI provider you select to generate the response. We don't store it beyond the request, and we don't share it with anyone else.

What about "free" models?

We don't ship free models that require sharing your data with the upstream provider. If a free tier's terms allow training on user prompts, we don't list it.

How is this different from OpenRouter or Portkey?

Pay-per-call USDC on Base or Solana via x402. No account, no API key, no subscription. Auto-fallback when a model is down. SDKs are OpenAI-compatible.

Why USDC instead of a subscription?

Agents can hold USDC; agents can't hold a credit card. Settlement happens on-chain in the same request via the x402 protocol — no prepaid credits, no minimum spend.

What happens if a model is down?

We auto-fallback to a comparable model and surface which one served you via the X-Fallback-Model response header, so your application never sees a hard failure.

Are the SDKs OpenAI-compatible?

Yes. Change base_url and you're done — every endpoint matches OpenAI's shape. @blockrun/llm for TypeScript, blockrun-llm for Python, both MIT-licensed.

Can I use this in production?

Yes. We run on Base mainnet with 1M+ calls per month. Use testnet.blockrun.ai for development against Base Sepolia.

Per call. Per token. No subscription.

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

The AI agent that pays
for its own AI.

Franklin holds USDC and spends it on the AI it needs — picks the best model per task, buys trading data, generates images, searches the web. You set the budget. It runs it. The wallet pays for inference, not real-world purchases.

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 · ~/workwallet 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.

FreeTry without paying — no card, no signup

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

Kimi K2.6

moonshot$0.95 / $4.00

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

Service marketplace

AI buys data & runtime.

Any API. Any agent. Pay per request with USDC via x402 — no keys, no subscriptions, no accounts.

live

Web Search

Exa

Neural search, find similar pages, extract content, grounded answers.

Polymarket, Kalshi, dFlow, Binance Futures data for agents.

Isolated code runtime for agents. Sandbox sessions, execute, inspect.

create $0.01 · ops $0.001

Add yours

List a data source

On-chain data, financial feeds, niche APIs — we onboard weekly.

Enterprise

AI infrastructure
for teams.

Budget controls, usage analytics, team management, and dedicated support for production AI deployments.

Contact sales Partner with us →

Budget controls: Per-key spend caps, hard limits, alerts
Usage analytics: Per-team, per-model, per-call attribution
Team management: SSO, roles, audit log, key rotation
Dedicated support: Slack channel, SLA, named CSM

Trust / Defaults

We don't share
your data.

Your prompt goes to the AI provider you picked. Nothing else, nowhere else. No training, no retention beyond the request, no profile linking.

Read the privacy policy Terms →

We don't share your data: No training, no retention beyond the request. Your prompt is forwarded only to the AI provider you select.
No accounts, no KYC: Wallet in, prompt out. Pseudonymous by default — no email, no phone number, no identity documents.
Open-source SDKs, MIT: Read the code, audit the wire format, run it yourself. @blockrun/llm and blockrun-llm on npm and PyPI.

Live / Network

Monthly calls

1M+

Countries

50+

Models

54+

Chains

Base · Sol

FAQ

Questions we get
before you ask them.

Do you train on my prompts?: No. We forward your prompt only to the AI provider you select to generate the response. We don't store it beyond the request, and we don't share it with anyone else.
What about "free" models?: We don't ship free models that require sharing your data with the upstream provider. If a free tier's terms allow training on user prompts, we don't list it.
How is this different from OpenRouter or Portkey?: Pay-per-call USDC on Base or Solana via x402. No account, no API key, no subscription. Auto-fallback when a model is down. SDKs are OpenAI-compatible.
Why USDC instead of a subscription?: Agents can hold USDC; agents can't hold a credit card. Settlement happens on-chain in the same request via the x402 protocol — no prepaid credits, no minimum spend.
What happens if a model is down?: We auto-fallback to a comparable model and surface which one served you via the X-Fallback-Model response header, so your application never sees a hard failure.
Are the SDKs OpenAI-compatible?: Yes. Change base_url and you're done — every endpoint matches OpenAI's shape. @blockrun/llm for TypeScript, blockrun-llm for Python, both MIT-licensed.
Can I use this in production?: Yes. We run on Base mainnet with 1M+ calls per month. Use testnet.blockrun.ai for development against Base Sepolia.

Read the docs Privacy policy →

Ship today

No keys. No subscriptions.
Just pay-per-call.

Get started Read the docs →

Pay-per-callAI gateway.

Cut AI costsby up to 78%.

The AI agent that paysfor its own AI.

One install.8 agent tools.

55+ models.One endpoint.

AI buys data & runtime.

AI infrastructurefor teams.

We don't shareyour data.

Questions we getbefore you ask them.

No keys. No subscriptions.Just pay-per-call.

Pay-per-call
AI gateway.

Cut AI costs
by up to 78%.

The AI agent that pays
for its own AI.

One install.
8 agent tools.

55+ models.
One endpoint.

AI infrastructure
for teams.

We don't share
your data.

Questions we get
before you ask them.

No keys. No subscriptions.
Just pay-per-call.