Документация API gpt-5.6-sol-fast — OpenAI через dreamtoai

gpt-5.6-sol-fast

ТекстOpenAIGPTgpt-5.6-sol-fast

Открыть Playground Управление API-ключами

GPT-5.5 是 OpenAI 的高阶通用文本模型，适合复杂问答、长文本分析、代码生成、方案推理、资料整理和高质量内容创作。它适合作为质量优先的主力模型，用于需要稳定理解能力和较强综合判断的业务场景。

Аутентификация

Base URL: https://api.dreamtoai.com
Authorization: Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
Имя модели (model): gpt-5.6-sol-fast

Протокол интеграции

Почему этот протокол

适合已有 OpenAI SDK、Chat Completions 代码或统一网关接入的用户。

URL эндпоинта

POST/v1/chat/completions

Authorization: Bearer YOUR_API_KEYContent-Type: application/json

JSON запроса и ответа

Запрос

{
  "model": "gpt-5.6-sol-fast",
  "messages": [
    {
      "content": "你好，世界",
      "role": "user"
    }
  ],
  "system_instruction": "你是一个严谨的助手。",
  "temperature": 0.7,
  "top_p": 1,
  "max_tokens": 4096,
  "stream": false,
  "reasoning_effort": "medium",
  "response_format": {
    "type": "json_object"
  },
  "tools": [],
  "tool_choice": "auto"
}

Ответ

{
  "id": "chatcmpl_example",
  "model": "gpt-5.5",
  "choices": [
    {
      "message": {
        "content": "你好，世界"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 16,
    "total_tokens": 24
  }
}

Поля запроса и ответа

Поля запроса

Поле	Тип	Обязательно
messages	array	Y
system_instruction	string	N
temperature	number	N
top_p	number	N
max_tokens	integer	N
stream	boolean	N
reasoning_effort	enum	N
response_format	object	N
tools	array	N
tool_choice	string	N

Поля ответа

Поле	Тип	Обязательно
id	string	N
model	string	N
choices[].message.content	string	N
usage.prompt_tokens	integer	N
usage.completion_tokens	integer	N
usage.total_tokens	integer	N

Примеры кода

cURLrequest.sh

curl -X POST "https://api.dreamtoai.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "gpt-5.6-sol-fast",
  "messages": [
    {
      "content": "你好，世界",
      "role": "user"
    }
  ],
  "system_instruction": "你是一个严谨的助手。",
  "temperature": 0.7,
  "top_p": 1,
  "max_tokens": 4096,
  "stream": false,
  "reasoning_effort": "medium",
  "response_format": {
    "type": "json_object"
  },
  "tools": [],
  "tool_choice": "auto"
}'