OpenAI-compatible chat completions across every frontier model on one endpoint — GPT-5, Claude, Gemini, Grok, DeepSeek, Llama, Mistral and ~290 more. POST { model, messages, max_tokens?, temperature?, top_p?, stop? } and get back a standard chat.completion (choices[].message + usage). Pay per call in USDC via x402 — no accounts, no provider keys, no subscriptions. Price scales with the model and max_tokens and is quoted in the 402. List selectable models at GET /api/ai/models.
/api/ai/chatPAYMENT-SIGNATURE.The chat API is a pay-per-call ai endpoint built for AI agents and autonomous software. OpenAI-compatible chat completions across every frontier model on one endpoint — GPT-5, Claude, Gemini, Grok, DeepSeek, Llama, Mistral and ~290 more.
There is no signup and no API key. An agent (or any HTTP client) hits the endpoint, receives an x402 "402 Payment Required" challenge, signs a sub-cent USDC payment on Base or Solana, and retries — the data comes back on the paid request. That makes it a drop-in chat data source for an agent tool-use loop, an MCP host, or a backend that needs ai data on demand without onboarding to yet another vendor portal.
| Name | Type | Description |
|---|---|---|
modelrequired | string | Gateway model id, e.g. openai/gpt-5, anthropic/claude-opus-4.8, google/gemini-3-pro-preview. Full list: GET /api/ai/models. min 1 chars · max 80 chars |
messagesrequired | array | OpenAI-style message list. |
max_tokens | integer | Max output tokens (default 1024). min 1 · max 8192 |
temperature | number | min 0 · max 2 |
top_p | number | min 0 · max 1 |
stop |
# 1. Probe the endpoint with no auth — receive 402 with PaymentRequirements
curl -sS -X POST 'https://2s.io/api/ai/chat' \
-H 'Content-Type: application/json' \
-d '{"model":"example","messages":[{"role":"system","content":"example"}],"max_tokens":1,"temperature":0,"top_p":0,"stop":"example"}'
# 2. Sign the EIP-3009 transferWithAuthorization for the advertised price +
# payTo from the 402 envelope, then retry with PAYMENT-SIGNATURE:
curl -sS -X POST 'https://2s.io/api/ai/chat' \
-H 'Content-Type: application/json' \
-H 'PAYMENT-SIGNATURE: <base64-json-payload>' \
-d '{"model":"example","messages":[{"role":"system","content":"example"}],"max_tokens":1,"temperature":0,"top_p":0,"stop":"example"}'
# Or just use the canonical runner — it handles the whole loop:
# EVM_PRIVATE_KEY=0x... node --env-file=.env.local \
# --experimental-strip-types scripts/x402-pay.ts \
# 'https://2s.io/api/ai/chat'import { TwoS } from '@2sio/sdk'
const client = new TwoS({
privateKey: process.env.EVM_PRIVATE_KEY as `0x${string}`,
})
const result = await client.ai.chat({
"model": "example",
"messages": [
{
"role": "system",
"content": "example"
}
],
"max_tokens": 1,
"temperature": 0,
"top_p": 0,
"stop": "example"
})
console.log('endpoint:', result.endpoint)
console.log('cost:', result.costUsd, 'USDC')
console.log('tx:', result.settlement?.txHash)
console.log('data:', result.data)import os
from twosio import TwoS
client = TwoS(private_key=os.environ["EVM_PRIVATE_KEY"])
result = client.ai.chat(model="example", messages=[{"role":"system","content":"example"}], max_tokens=1, temperature=0, top_p=0, stop="example")
print("endpoint:", result.endpoint)
print("cost:", result.cost_usd, "USDC")
print("tx:", (result.settlement or {}).get("tx_hash"))
print("data:", result.data)// 1. Add @2sio/mcp to your MCP host config (Claude Desktop example below).
// EVM_PRIVATE_KEY funds x402 payments per call.
// claude_desktop_config.json
{
"mcpServers": {
"2sio": {
"command": "npx",
"args": ["-y", "@2sio/mcp"],
"env": { "EVM_PRIVATE_KEY": "0x..." }
}
}
}
// 2. Once the server is running, agents call this tool via standard MCP:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "ai.chat",
"arguments": {
"model": "example",
"messages": [
{
"role": "system",
"content": "example"
}
],
"max_tokens": 1,
"temperature": 0,
"top_p": 0,
"stop": "example"
}
}
}