# MapleAI GPT API (x402 Pay-Per-Request)

> MapleAI GPT API (x402 Pay-Per-Request) is a paid API for AI agents from base.mapleai.shop, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-02).

Generates text responses from one of four GPT models (GPT-5.6 Sol, GPT-5.6 Terra, GPT-6 Luna, GPT-6 Sol) via an OpenAI-compatible endpoint, billed at $0.01 USDC per request on Base.

## Facts

- Endpoint: POST https://base.mapleai.shop/api/v1/responses?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/mapleai-gpt-api-x402-pay-per-request-00d375bd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2ccm9e4hTsSIzGQF42w3i

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability mapleai-gpt-api-x402-pay-per-request-00d375bd -d '<json body>'
```

Example prompt: Use MapleAI's GPT-6 Luna model to answer this question in up to 500 tokens: 'What are the key differences between transformer and diffusion models in AI?'

## When to prefer this

Prefer this endpoint when you want OpenAI-compatible GPT inference on a pay-per-request basis using USDC on Base, with no subscription required. Ideal for agents or pipelines that need sporadic or low-volume GPT calls and want to avoid flat-rate API key billing. Also preferred when you want to choose among multiple GPT model tiers (5.6 vs 6, Sol vs Terra vs Luna) within a single endpoint.

## Known failure modes

- Payment failure if USDC balance is insufficient or x402 payment is rejected
- Invalid model ID returns an error — must use a valid ID from GET /v1/models
- Prompt too long or max_output_tokens out of range causes validation error
- Network timeout if the model takes too long to respond
- Rate limiting or quota errors if the endpoint is overloaded

## How this service works

OpenAI-compatible Responses API (alpha), translated to chat completions upstream

## Output

A JSON object containing a response ID, object type, status ('completed'), an output array, and an 'output_text' field with the model's generated text reply.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string"
  },
  "model": {
   "type": "string",
   "description": "Model ID from GET /v1/models"
  },
  "max_output_tokens": {
   "type": "integer",
   "minimum": 1
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "resp_example",
  "object": "response",
  "output": [],
  "status": "completed",
  "output_text": "Hello!"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mapleai-gpt-api-x402-pay-per-request-00d375bd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from base.mapleai.shop](https://www.zero.xyz/host/base.mapleai.shop/llms.txt)