GPT-5.4 - 完整参数文档

curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "请介绍一下你自己"
    }
  ]
}
'

{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gpt-5.4",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！我是 GPT-5.4，拥有更强的推理和理解能力。我在处理复杂问题、多步骤推理和代码生成方面表现出色。\\n\\n主要特点包括：\\n- 更强的逻辑推理能力\\n- 更好的上下文理解\\n- 更准确的代码生成"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 1891,
    "total_tokens": 1904,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 13,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 1480
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/billing"
  }
}

{
  "error": {
    "code": 403,
    "message": "Access denied for this model",
    "type": "permission_error",
    "param": "model"
  }
}

{
  "error": {
    "code": 404,
    "message": "Specified model not found",
    "type": "not_found_error",
    "param": "model",
    "fallback_suggestion": "gpt-5.4"
  }
}

{
  "error": {
    "code": 413,
    "message": "Image file too large",
    "type": "request_too_large_error",
    "param": "content",
    "fallback_suggestion": "compress image to under 10MB"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 502,
    "message": "Upstream AI service unavailable",
    "type": "upstream_error",
    "fallback_suggestion": "try different model"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}

POST

chat

completions

curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "请介绍一下你自己"
    }
  ]
}
'

{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gpt-5.4",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！我是 GPT-5.4，拥有更强的推理和理解能力。我在处理复杂问题、多步骤推理和代码生成方面表现出色。\\n\\n主要特点包括：\\n- 更强的逻辑推理能力\\n- 更好的上下文理解\\n- 更准确的代码生成"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 1891,
    "total_tokens": 1904,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 13,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 1480
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/billing"
  }
}

{
  "error": {
    "code": 403,
    "message": "Access denied for this model",
    "type": "permission_error",
    "param": "model"
  }
}

{
  "error": {
    "code": 404,
    "message": "Specified model not found",
    "type": "not_found_error",
    "param": "model",
    "fallback_suggestion": "gpt-5.4"
  }
}

{
  "error": {
    "code": 413,
    "message": "Image file too large",
    "type": "request_too_large_error",
    "param": "content",
    "fallback_suggestion": "compress image to under 10MB"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 502,
    "message": "Upstream AI service unavailable",
    "type": "upstream_error",
    "fallback_suggestion": "try different model"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}

BaseURL 说明：默认 BaseURL 为 https://direct.evolink.ai，对文本模型支持更好，支持长连接；https://api.evolink.ai 是多模态主力地址，对文本模型作为备用地址使用。

授权

Authorization

string

header

必填

##所有接口均需要使用Bearer Token进行认证##

获取 API Key：

访问 API Key 管理页面获取您的 API Key

使用时在请求头中添加：

Authorization: Bearer YOUR_API_KEY

请求体

application/json

model

enum<string>

默认值:gpt-5.4

必填

对话模型名称

可用选项:

gpt-5.4

示例:

"gpt-5.4"

messages

object[]

必填

对话消息列表，支持多轮对话和多模态输入（文本、图片）

Minimum array length: 1

Show child attributes

stream

boolean

是否以流式方式返回响应

true: 流式返回，逐块实时返回内容
false: 等待完整响应后一次性返回

示例:

false

temperature

number

采样温度，控制输出的随机性

说明:

较低值(如 0.2): 更确定、更聚焦的输出
较高值(如 1.5): 更随机、更有创意的输出

必填范围: 0 <= x <= 2

示例:

0.7

top_p

number

核采样(Nucleus Sampling)参数

说明:

控制从累积概率前多少的token中采样
例如 0.9 表示从累积概率达到90%的token中选择
默认值: 1.0（考虑所有token）

建议: 不要同时调整 temperature 和 top_p

必填范围: 0 <= x <= 1

示例:

0.9

top_k

integer

Top-K 采样参数

说明:

例如 10 表示限制每次采样时只考虑概率最高的 10 个 token
较小的值会使输出更加聚焦
默认不限制

必填范围: x >= 1

示例:

40

响应

对话生成成功

string

对话完成的唯一标识符

示例:

"chatcmpl-20251010015944503180122WJNB8Eid"

model

string

实际使用的模型名称

示例:

"gpt-5.4"

object

enum<string>

响应类型

可用选项:

chat.completion

示例:

"chat.completion"

created

integer

创建时间戳

示例:

1760032810

choices

object[]

对话生成的选择列表

Show child attributes

usage

object

Token 使用统计信息

Show child attributes

GPT-5.4 - 快速开始 GPT-5.2 - 快速开始

图像系列

视频系列

音频系列

语言系列

账户管理

任务管理

文件管理

GPT-5.4 - 完整参数文档

授权

请求体

响应