$ GET /pricing

Pricing

Pay in compute with a proof-of-work puzzle, or settle micro-amounts per call in USDC or USDG on fourteen chains. No minimum; card welcome at /reports, and monitors are the one subscription ($5, cancel anytime). The wallet is the identity.

FREE · PROOF-OF-WORK
$0.00 / call

Solve a short sha256 puzzle - about 65,536 sha256 hashes on average, a fraction of a second of CPU on a laptop - instead of paying. No wallet at all.

✓ 170 pure-CPU tools
✓ Nothing to fund
✓ Hosted MCP connector runs these free
· Rate-limited; browser/GPU tools excluded
x402
PAID · STABLECOIN OVER x402 OR MPP
$0.001 / call & up

An x402 or MPP client signs the stablecoin payment from the agent's own wallet and retries, settling in seconds.

x402 takes USDC on Base, Solana, Polygon, Arbitrum, Monad, Celo, Avalanche, Sei, Optimism, Arc, Ink, Stellar, or Algorand - or USDG on Robinhood Chain; MPP also settles natively on Tempo.

✓ All 628 tools, including browser & memory
✓ A fixed price per tool call; metered model calls settle actual usage under the quote
✓ Non-custodial on this rail - you sign, we hold no balance
✓ Spend caps refuse a runaway model before paying
// from-price by category

What each call costs.

Most tools - text, math, encoding, time, validation, convertfrom $0.001
Agent memory - write, recall, grant, auditfrom $0.001
Payments & x402 - decode, verify, quote, auditfrom $0.001
Article extract - clean markdown out$0.01
Headless browser - render & screenshot (real Chromium)from $0.004
Web search & cited answers - search, news, answerfrom $0.01
Market data - stock and crypto quotes, perp fundingfrom $0.001
Text to speech - three voice tiersfrom $0.005
Transcription - audio to textfrom $0.03
live machine-readable pricesGET /api/pricingGET /openapi.json
// POST /v1/*

The /v1 LLM gateway.

Point any OpenAI SDK at base_url https://agent402.tools/v1/metered and every request is quoted from its own body before payment, then settled at what the call actually used, under that quote. The flat tiers below stay for callers that want one fixed price; omit the model on the auto tier and the gateway picks one for the prompt.

/v1/metered/chat/completions - quoted per request, settles actual usage under the quotefrom $0.001
/v1/metered/messages - Anthropic Messages wire, quoted per requestfrom $0.001
/v1/embeddings - default-on cache, same payer's repeat free$0.002
/v1/nano/chat/completions - high-frequency agent loops$0.003
/v1/auto/chat/completions - model optional, eval-ranked routing$0.01
/v1/chat/completions - budget/mid models$0.02
/v1/images/generations - one image per call$0.08
/v1/audio/speech - OpenAI TTS wire, mp3/pcm bytes out$0.06
/v1/pro/chat/completions - frontier models$0.10
/v1/premium/chat/completions - the largest models$0.50
full wire format: /docs

A credits key already issued also works as the API key.

Paying for many calls

Paying exact over x402 signs one authorization and waits on one settlement per request: fine for ten calls, the wrong shape for ten thousand. On the metered gateway one approval turns each quote into a ceiling, still priced per request and settled only on a 200.

Keep the wallet · approve once

A one-time Permit2 approval for USDC on Base (one on-chain transaction, which needs a little ETH on Base for gas) lets the gateway settle the actual usage under each quote, with no fixed tier to overpay into. Non-custodial on this rail, and the approval is yours to revoke.

npx agent402-openclaw permit2-approve

The approval belongs to the wallet, so it applies to any client that pays from it, not only OpenClaw.

Start on the free tier

Quickstart → Browse tools