API免费额度发放中，总量$999,前往查看额度。
模型
体验中心
赛事
文档
资源
控制台
O

gpt-5.5

OpenAI模型 IDgpt-5.5
O

gpt-5.5

OpenAI模型 IDgpt-5.5

GPT-5.5 is OpenAI's flagship large language model released on April 24, 2026. Positioned as a new form of intelligence for real-world work and agents, its core breakthrough is autonomous planning and execution of multi-step complex tasks. It excels in programming, computer operation, scientific research analysis, and other areas, delivering higher efficiency with fewer token costs. The suffixes high/low/medium/xhigh indicate reasoning effort level.

模式文件 / 图像 / 文本 → 文本
输入价格$1 / 1M tokens 参考价
输出价格$12 / 1M tokens 参考价
上下文长度1050K tokens

能力与限制

适用场景
ReasoningToolsTool ChoiceStructured OutputsVisionFilesWeb SearchCachingGPT1.1M
模型能力标签
推理工具调用工具选择结构化输出图像理解文件输入联网搜索缓存原生补丁应用
模型品牌
OpenAI
输入形式
文件 / 图像 / 文本
输出形式
文本
最大输出
128K tokens

价格 参考价

供应商计费类型价格摘要
O
openai
按量计费
输入价格$1per 1M tokens
补全价格$12per 1M tokens
缓存读取价格$2per 1M tokens
缓存创建价格$2per 1M tokens

接入使用

代码示例

curl https://aix-test.deepwl.cn/v1/chat/completions \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

将 <YOUR_API_KEY> 替换为你在令牌管理页面生成的 API Key。

认证方式

All requests must include the Authorization: Bearer <TOKEN> header.

接口路径

POST
openai

支持的参数

参数类型默认值说明
boolean-Deprecated alias for reasoning.exclude. When true, reasoning tokens are returned in the response when supported by the model.
integer-This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.
integer-This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.
map-Controls reasoning behavior for models that support thinking tokens, including whether reasoning is enabled, the reasoning effort, maximum reasoning tokens, and whether reasoning is excluded from the response.
map-Forces the model to produce specific output format. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Note**: when using JSON mode, you should also instruct the model to produce JSON yourself via a system or user message.
integer-If specified, the inferencing will sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed for some models.
boolean-If the model can return structured outputs using response\_format json\_schema.
string or object-Controls which (if any) tool is called by the model. 'none' means the model will not call any tool and instead generates a message. 'auto' means the model can pick between generating a message or calling one or more tools. 'required' means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool.
array-Tool calling parameter, following OpenAI's tool calling request shape. For non-OpenAI providers, it will be transformed accordingly. [Click here to learn more about tool calling](/docs/guides/features/tool-calling)

速率限制

RPM
501

RPM = 每分钟请求数。