๐Ÿค– GPT-OSS 2T API

Free, rate-limited AI API powered by GPT-OSS 2T

โœจ Model: gpt-oss:latest ๐Ÿš€ Fully Server-Side PHP ๐Ÿ”’ Rate Limited
๐ŸŽ‰ API is Live! Start making requests immediately โ€” no API key required.

๐Ÿ“ก Base URL

https://gpt.yzz.me/api

โšก Quick Start

JavaScript (Fetch API)

const response = await fetch('https://gpt.yzz.me/api', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    messages: [{ role: 'user', content: 'Hello!' }],
    stream: false,
    temperature: 0.8
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Python

import requests

response = requests.post(
    'https://gpt.yzz.me/api',
    json={
        'messages': [{'role': 'user', 'content': 'Hello!'}],
        'stream': False,
        'temperature': 0.8
    }
)

data = response.json()
print(data['choices'][0]['message']['content'])

cURL

curl -X POST https://gpt.yzz.me/api \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Hello!"}],"stream":false}'

๐Ÿ“ Request Parameters

ParameterTypeRequiredDescription
messagesarrayโœ… YesArray of message objects
streambooleanโŒ NoEnable streaming (default: true)
temperaturenumberโŒ NoSampling temperature 0.0-2.0 (default: 0.8)
max_tokensnumberโŒ NoMaximum tokens (default: -1)
top_pnumberโŒ NoNucleus sampling (default: 0.9)

๐Ÿ”’ Rate Limits

โš ๏ธ Per-IP Rate Limiting: Max 2 requests/second, 500ms minimum delay

๐Ÿงช Test the API

Health Check: GET https://gpt.yzz.me/api

Interactive Test: Test Page

๐Ÿ› ๏ธ Technical Details

Infrastructure:
  • Fully server-side PHP application
  • Automatic retry with exponential backoff (3 attempts)
  • Per-IP rate limiting and request queuing
  • Server-Sent Events (SSE) streaming
  • System prompt auto-injection