Chat API (o1-o3 series)

Short description: Chat endpoint for lightweight models in the o1/o3 series. Note: the o1 series typically does not support streaming responses.

---

Overview

• Method: POST
• Path: /v1/chat/completions
• Content-Type: application/json

Authentication

Supports common header-based authentication:

• OpenAI: Authorization: Bearer sk-xxx
• Anthropic: x-api-key: sk-xxx
• Google: x-goog-api-key: sk-xxx

---

Request example

Body parameters

Parameter	Type	Required	Description
model	string	yes	Model name, e.g. o1-mini, o1-preview
messages	array<object>	yes	Chat message array. role does not support system; items are `{ role: 'user'
max_completion_tokens	number	no	Max number of generated tokens
stream	boolean	no	Whether to stream responses; o1 series usually only supports false

Example:

{
  "model": "o1-mini",
  "messages": [{"role":"user","content":"Good evening"}],
  "max_completion_tokens": 1688,
  "stream": false
}

---

curl example

curl -X POST "https://api.gpt.ge/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxx" \
  -d '{"model":"o1-mini","messages":[{"role":"user","content":"Good evening"}],"max_completion_tokens":1688,"stream":false}'

JavaScript (fetch) example

fetch('https://api.gpt.ge/v1/chat/completions', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json', 'Authorization': 'Bearer sk-xxxx' },
  body: JSON.stringify({ model: 'o1-mini', messages: [{ role: 'user', content: 'Good evening' }], max_completion_tokens: 1688, stream: false })
}).then(r => r.json()).then(console.log)

Python (requests) example

import requests

payload = { 'model': 'o1-mini', 'messages': [{'role':'user','content':'Good evening'}], 'max_completion_tokens': 1688, 'stream': False }
resp = requests.post('https://api.gpt.ge/v1/chat/completions', headers={'Content-Type':'application/json','Authorization':'Bearer sk-xxxx'}, json=payload)
print(resp.json())

---

Response example (200)

{
  "id": "chatcmpl-A1iMgDLzZtUJ9QDpfqDLxKH0zfUnp",
  "object": "chat.completion",
  "created": 1724972230,
  "model": "o1-mini",
  "choices": [
    { "index": 0, "message": { "role": "assistant", "content": "Good evening! How can I help you?", "refusal": null }, "logprobs": null, "finish_reason": "stop" }
  ],
  "usage": { "prompt_tokens": 9, "completion_tokens": 10, "total_tokens": 19 },
  "system_fingerprint": "fp_157b3831f5"
}