Premium GPT access, no subscription.

Models

Current model rates are listed below.

Full catalog with live pricing: GET /v1/models

Images

Generate and edit images with a per-image x402 quote.

POST /api/v1/images/generations
POST /api/v1/images/image2image
Image API guide | OpenAPI

Audio

Text-to-speech (tts-1, tts-1-hd, orpheus-english, orpheus-arabic, $0.015/request) and speech-to-text (whisper-1, whisper-large-v3, whisper-large-v3-turbo, $0.006/request, word timestamps on whisper-large-v3*).

POST /v1/audio/speech   POST /v1/audio/transcriptions   Audio API guide

Jev

Structured decisions with jev-latest via SystemOne. $0.06 per 1M input tokens; output tokens are free.

POST /jev   Jev API guide

Agents

Autonomous task execution with agents/oss-20b: multi-step reasoning plus calculator and fetch_url tools. $0.002 base + $0.001 per step, charged at the max_steps ceiling.

POST /v1/agents/execute   Agents API guide

Prepaid API keys

Token packs for one GPT or Claude model: 0.1M-1M tokens at the model input rate, in 0.1M steps.

POST /prepaid/codes   API guide

Quickstart

OpenAI-compatible requests with x402 payment. An x402-aware client must sign and retry after the 402 challenge.

Free embeddings API — no key, no account
Run an example using free embeddings and paid GPT

# pip install openai
from openai import OpenAI

client = OpenAI(
  base_url="https://sol.mapleai.shop/v1",
  api_key="payment-signature-required"  # use an x402 client
)

response = client.chat.completions.create(
  model="openai/gpt-5.6-sol",
  messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

// npm install openai
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://sol.mapleai.shop/v1',
  apiKey: 'payment-signature-required'  // use an x402 client
});

const response = await client.chat.completions.create({
  model: 'openai/gpt-5.6-sol',
  messages: [{role: 'user', content: 'Hello'}]
});
console.log(response.choices[0].message.content);

curl https://sol.mapleai.shop/v1/chat/completions \
  -H 'content-type: application/json' \
  -d '{
    "model": "openai/gpt-5.6-sol",
    "messages": [{"role": "user", "content": "Hi"}]
  }'

# 402 Payment Required
# Response includes the USDC amount + payment details
# Sign with your wallet, retry with the signature

curl https://sol.mapleai.shop/api/v1/responses \
  -H 'content-type: application/json' \
  -d '{
    "model": "openai/gpt-5.6-sol",
    "input": "Explain x402 in one line"
  }'

# {"object":"response","output_text":"...", ...}

Payment

x402 protocol — priced upfront, settled on-chain.

1. Request without payment

   Send your OpenAI-compatible request to our endpoint. No auth header needed.

2. Receive 402 with exact price

   The response includes the precise USDC amount for your token count, the treasury address, and the accepted payment scheme.

3. Sign & retry with payment

   Your wallet signs the USDC transfer. The facilitator co-signs as fee payer (no native gas needed). Retry the request with the signature — it runs immediately.

Discovery

Machine-readable endpoints for AI agents and scanners.

curl https://sol.mapleai.shop/.well-known/x402

curl https://sol.mapleai.shop/v1/models