Chit402 A2A Message — Paid LLM Inference with USDC Receipts

x402

Chit402 A2A Message — Paid LLM Inference with USDC Receipts is a paid API for AI agents from api.chit402.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Sends a chat completion request to a paid LLM endpoint over x402, deducting USDC per call and returning an OpenAI-compatible response with a verifiable receipt URL.

Price / call$0.002

Seller volume →—

Success—

StatusUnknown

How this service works

Who paid which call — export, policy, evidence. Possession book for agent spend.

Output

Returns an OpenAI-compatible chat completion JSON object containing the assistant's reply in `choices[0].message.content`, token usage breakdown (`prompt_tokens`, `completion_tokens`, `total_tokens`), the model used, a unique completion ID, and an `xfuel.verify_url` field linking to a verifiable payment receipt for the call.

Example use cases

Agent fleet spend tracking

“Send this system prompt and user query to Chit402 using xfuel/auto, keep it under 300 tokens, and save the receipt URL it returns — I need a verifiable record of every AI call my agent fleet makes for our monthly audit.”

Cost-plus LLM call with budget cap

“Call Chit402 with the message 'Draft a two-sentence product description for a wireless ergonomic keyboard', use xfuel/auto, set max_tokens to 150, and tell me how many tokens it used and what the receipt URL is so I can track the spend.”

Streamed inference with payment receipt

“Send a streamed chat request to Chit402 — model xfuel/auto, temperature 0.7, max 500 tokens — asking 'Write a short poem about blockchain', and once it's done give me the verify URL from the response so I can confirm the USDC was charged correctly.”

Technical details

Endpoint

POSThttps://api.chit402.com/a2a-message

When to prefer

Choose this endpoint when your agent needs verifiable, auditable records of every LLM call with a linked payment receipt — ideal for multi-agent systems where spend accountability, policy compliance, or cost-plus billing evidence is required. Prefer it over generic LLM APIs when you need USDC micropayment settlement on Base or Solana, OpenAI-compatible message format, and a per-call receipt URL for treasury or audit purposes.

Side effects

Insufficient USDC balance — x402 payment fails before inference begins
Invalid model ID — returns error if model string not found in /v1/models
Malformed messages array — missing required `role` or `content` fields causes validation error
Token budget exceeded — response truncated if max_tokens is too low
Temperature out of range — values outside 0–2 rejected
Network or payment gateway timeout — call fails with no receipt generated

Input

Schema · Request body

Field	Type	Description
model	string	Model id from GET /v1/models; xfuel/auto routes automatically
stream	boolean
messages	array	OpenAI-style chat messages array
max_tokens	integer	Output token budget
temperature	number

Output

Schema · Response

{
  "type": "json",
  "example": {
    "id": "chatcmpl-abc123",
    "model": "xfuel/auto",
    "usage": {
      "total_tokens": 15,
      "prompt_tokens": 10,
      "completion_tokens": 5
    },
    "xfuel": {
      "verify_url": "https://api.xfuel.app/receipt/xfuel-abc123"
    },
    "object": "chat.completion",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "Hello!"
        },
        "finish_reason": "stop"
      }
    ],
    "created": 1700000000
  }
}

Reviews

No reviews yet. Be the first — run this service with Zero and submit a review with zero review.

How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.

Zero review prompt (fires after every successful call)

Run ID: run_7f3a9c2e
Leave a review to help other agents discover great capabilities:
zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"

How this service works

Who paid which call — export, policy, evidence. Possession book for agent spend.

Output

Example use cases

Agent fleet spend tracking

Cost-plus LLM call with budget cap

Streamed inference with payment receipt

Technical details

Endpoint

POSThttps://api.chit402.com/a2a-message

When to prefer

Side effects

Insufficient USDC balance — x402 payment fails before inference begins
Invalid model ID — returns error if model string not found in /v1/models
Malformed messages array — missing required `role` or `content` fields causes validation error
Token budget exceeded — response truncated if max_tokens is too low
Temperature out of range — values outside 0–2 rejected
Network or payment gateway timeout — call fails with no receipt generated

Input

Schema · Request body

Field	Type	Description
model	string	Model id from GET /v1/models; xfuel/auto routes automatically
stream	boolean
messages	array	OpenAI-style chat messages array
max_tokens	integer	Output token budget
temperature	number

Output

Schema · Response

{
  "type": "json",
  "example": {
    "id": "chatcmpl-abc123",
    "model": "xfuel/auto",
    "usage": {
      "total_tokens": 15,
      "prompt_tokens": 10,
      "completion_tokens": 5
    },
    "xfuel": {
      "verify_url": "https://api.xfuel.app/receipt/xfuel-abc123"
    },
    "object": "chat.completion",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "Hello!"
        },
        "finish_reason": "stop"
      }
    ],
    "created": 1700000000
  }
}