GPT-5.5 Chat | ToAPIs Documentation

POST

/v1/chat/completions

중국 본토 사용자 안내: 중국 본토 사용자는 https://toapis.cn 를 API 엔드포인트(Base URL)로 사용해 주세요. 본 문서의 예시에서 https://toapis.com 을 https://toapis.cn 로 바꿔 주세요.

OpenAI-compatible Chat Completions API
Select the gpt-5.5 model via the model parameter
Supports streaming output (SSE)
Supports multi-turn conversation, system prompts, and vision input

Authorizations

Authorizationstring헤더필수

All endpoints require Bearer Token authentication

Get your API Key from the API Key Management Page

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

modelstring본문필수기본값: gpt-5.5

모델 name

Example: "gpt-5.5"

messagesobject[]본문필수

List of conversation messages in chronological order

messages[n]

rolestring본문필수

Message role — system, user, or assistant

contentstring본문필수

Message content — string or array of content blocks (supports images)

streamboolean본문기본값: false

Whether to enable streaming output (Server-Sent Events)

true: Stream tokens incrementally
false: Return the complete response at once

max_tokensinteger본문

Maximum number of tokens to generate

Uses the model's default limit when not set

temperaturenumber본문기본값: 1

Sampling temperature, controls output randomness

Range: 0 to 2
Lower values produce more deterministic output; higher values produce more varied output

top_pnumber본문기본값: 1

Nucleus sampling probability threshold

Range: 0 to 1. It is not recommended to modify both temperature and top_p at the same time

stopstring | string[]본문

Stop sequences — generation stops when these strings are encountered

Maximum 4 stop sequences

응답

idstring

Unique identifier for this request

objectstring

Object type, always chat.completion

createdinteger

Request creation timestamp (Unix)

modelstring

The model that was actually used

choicesobject[]

List of generated results

choices[].message.role: Message role, always assistant
choices[].message.content: Generated text content
choices[].finish_reason: Stop reason — stop / length / content_filter
choices[].index: Result index

usageobject

Token usage statistics for this request

usage.prompt_tokens: Input token count
usage.completion_tokens: Output token count
usage.total_tokens: Total token count

요청 예시

curl --request POST \
  --url https://toapis.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "user",
        "content": "Hello, please introduce yourself"
      }
    ]
  }'

curl --request POST \
  --url https://toapis.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "system",
        "content": "You are a professional code assistant"
      },
      {
        "role": "user",
        "content": "Write a quicksort in Python"
      }
    ],
    "stream": true
  }'

curl --request POST \
  --url https://toapis.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://www.gstatic.com/webp/gallery/1.jpg"
            }
          }
        ]
      }
    ],
    "max_tokens": 300
  }'

from openai import OpenAI

client = OpenAI(
    api_key="your-ToAPIs-key",
    base_url="https://toapis.com/v1"
)

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[
        {"role": "user", "content": "Hello, please introduce yourself"}
    ]
)

print(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    api_key="your-ToAPIs-key",
    base_url="https://toapis.com/v1"
)

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What is in this image?"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}
                }
            ]
        }
    ],
    max_tokens=300
)

print(response.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    api_key="your-ToAPIs-key",
    base_url="https://toapis.com/v1"
)

stream = client.chat.completions.create(
    model="gpt-5.5",
    messages=[
        {"role": "system", "content": "You are a professional code assistant"},
        {"role": "user", "content": "Write a quicksort in Python"}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your-ToAPIs-key",
  baseURL: "https://toapis.com/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [{ role: "user", content: "Hello, please introduce yourself" }],
});

console.log(response.choices[0].message.content);

응답 예시

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1703884800,
  "model": "gpt-5.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm GPT-5.5, the latest model in OpenAI's fifth-generation series. I have enhanced capabilities in reasoning, code generation, and multimodal understanding. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 42,
    "total_tokens": 55
  }
}

{
  "error": {
    "code": "invalid_request_error",
    "message": "The 'messages' field is required.",
    "param": "messages",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid API key",
    "type": "authentication_error"
  }
}