响应

使用 CometAPI 的 POST /v1/responses 生成高级模型输出，支持多模态输入、有状态聊天、内置工具和函数调用。

POST /v1/responses

Python

Text Input

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key="<COMETAPI_KEY>",
)

response = client.responses.create(
    model="gpt-5.4",
    input="Tell me a three sentence bedtime story about a unicorn.",
)

print(response.output_text)

200

{
  "id": "resp_0a153ae8201f73bc0069a7e8044cc481",
  "object": "response",
  "created_at": 1772611588,
  "status": "completed",
  "background": false,
  "completed_at": 1772611589,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "gpt-4.1-nano",
  "output": [
    {
      "id": "msg_0a153ae8201f73bc0069a7e8049a8881",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "text": "Four."
        }
      ],
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": null,
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "auto",
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 19,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 9,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 28
  },
  "user": null,
  "metadata": {}
}

​

概述

Responses API 是 CometAPI 的高级模型响应生成端点。相比聊天补全，它提供了更丰富的接口，内置支持多模态输入、有状态对话、工具集成和结构化输出——全部通过单个端点实现。

​

核心能力

• 多模态输入 — 接受文本、图像、文件（包括 PDF）和 URL 作为输入
• 有状态对话 — 使用 previous_response_id 或 conversation 将响应串联起来，无需自行管理消息历史
• 内置工具 — 无需任何设置即可使用 web_search_preview、file_search、code_interpreter 等工具
• 函数调用（Function Calling） — 定义模型可调用的自定义函数，并传入结构化参数
• 结构化输出 — 通过 text.format 参数请求符合 JSON Schema 的输出
• 推理模型 — 对于 o-series 和 gpt-5 模型，可通过 reasoning.effort 参数配置推理深度
• 流式输出（Streaming） — 通过 SSE 流式传输响应，并提供细粒度事件类型（response.output_text.delta、response.completed 等）

​

重要说明

模型差异 — 不同模型提供商可能支持不同的请求参数，并返回不同的响应字段。CometAPI 上可用的模型并非都支持所有参数。

透传原则 — CometAPI 会将请求转发给模型提供商，并原样返回其响应，确保你获得与原始 API 一致的输出。响应对象会回显许多请求参数（如 temperature、tools、reasoning），以提高透明度。

​

流式事件

当 stream 设置为 true 时，API 会按以下顺序发送服务器发送事件（SSE）：

1. response.created — 响应对象已初始化
2. response.in_progress — 生成已开始
3. response.output_item.added — 新的输出项（消息或工具调用）
4. response.content_part.added — 内容部分已开始
5. response.output_text.delta — 文本分块（包含 delta 字段，其中包含文本片段）
6. response.output_text.done — 该内容部分的文本生成完成
7. response.content_part.done — 内容部分已完成
8. response.output_item.done — 输出项已完成
9. response.completed — 完整响应，包含 usage 数据

​

参考文档

有关详细参数说明，请参阅上方的交互式 API playground。关于提供商文档，请参阅：

• 文本输入与输出
• 图像输入
• 文件输入（PDF）
• 结构化输出
• 函数调用（Function Calling）
• 对话状态
• 内置工具
• 推理模型

---

授权

Authorization · string · header · 必填

Bearer token authentication. Use your CometAPI key.

请求体

application/json

model · string · 必填

Model ID to use for this request. See the Models page for current options.

示例:

"gpt-5.4"

input · string object[] · 必填

Text, image, or file inputs to the model, used to generate a response. Can be a simple string for text-only input, or an array of input items for multimodal content (images, files) and multi-turn conversations.

instructions · string

A system (or developer) message inserted into the model's context. When used with previous_response_id, instructions from the previous response are not carried over — this makes it easy to swap system messages between turns.

background · boolean · 默认值: false

Whether to run the model response in the background. Background responses do not return output directly — you retrieve the result later via the response ID.

context_management · object[]

Context management configuration for this request. Controls how the model manages context when the conversation exceeds the context window.

Show child attributes

conversation · string object

The conversation this response belongs to. Items from the conversation are prepended to input for context. Input and output items are automatically added to the conversation after the response completes. Cannot be used with previous_response_id.

include · enum<string>[]

Additional output data to include in the response. Use this to request extra information that is not included by default.

可用选项: web_search_call.action.sources, code_interpreter_call.outputs, computer_call_output.output.image_url, file_search_call.results, message.input_image.image_url, message.output_text.logprobs, reasoning.encrypted_content

max_output_tokens · integer

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

max_tool_calls · integer

The maximum number of total calls to built-in tools that can be processed in a response. This limit applies across all built-in tool calls, not per individual tool. Any further tool call attempts by the model will be ignored.

metadata · object

Set of up to 16 key-value pairs that can be attached to the response. Useful for storing additional information in a structured format. Keys have a maximum length of 64 characters; values have a maximum length of 512 characters.

Show child attributes

parallel_tool_calls · boolean · 默认值: true

Whether to allow the model to run tool calls in parallel.

previous_response_id · string

The unique ID of a previous response. Use this to create multi-turn conversations without manually managing conversation state. Cannot be used with conversation.

prompt · object

Reference to a prompt template and its variables.

Show child attributes

prompt_cache_key · string

A key used to cache responses for similar requests, helping optimize cache hit rates. Replaces the deprecated user field for caching purposes.

prompt_cache_retention · enum<string>

The retention policy for the prompt cache. Set to 24h to keep cached prefixes active for up to 24 hours.

可用选项: in-memory, 24h

reasoning · object

Configuration options for reasoning models (o-series and gpt-5). Controls the depth of reasoning before generating a response.

Show child attributes

safety_identifier · string

A stable identifier for your end-users, used to help detect policy violations. Should be a hashed username or email — do not send identifying information directly.

Maximum string length: 64

service_tier · enum<string>

Specifies the processing tier for the request. When set, the response will include the actual service_tier used.

• auto: Uses the tier configured in project settings (default behavior).
• default: Standard pricing and performance.
• flex: Flexible processing with potential cost savings.
• priority: Priority processing with faster response times.

可用选项: auto, default, flex, priority

store · boolean · 默认值: true

Whether to store the generated response for later retrieval via API.

stream · boolean · 默认值: false

If set to true, the response data will be streamed to the client as it is generated using server-sent events (SSE). Events include response.created, response.output_text.delta, response.completed, and more.

stream_options · object

Options for streaming responses. Only set this when stream is true.

Show child attributes

temperature · number · 默认值: 1

Sampling temperature between 0 and 2. Higher values (e.g., 0.8) increase randomness; lower values (e.g., 0.2) make output more focused and deterministic. We recommend adjusting either this or top_p, but not both.

必填范围: 0 <= x <= 2

text · object

Configuration for text output. Use this to request structured JSON output via JSON mode or JSON Schema.

Show child attributes

tool_choice · string object · 默认值: auto

Controls how the model selects which tool(s) to call.

• auto (default): The model decides whether and which tools to call.
• none: The model will not call any tools.
• required: The model must call at least one tool.
• An object specifying a particular tool to use.

tools · object[]

An array of tools the model may call while generating a response. CometAPI supports three categories:

• Built-in tools: Platform-provided tools like web_search_preview and file_search.
• Function calls: Custom functions you define, enabling the model to call your own code with structured arguments.
• MCP tools: Integrations with third-party systems via MCP servers.

top_logprobs · integer

Number of most likely tokens to return at each position (0–20), each with an associated log probability. Must include message.output_text.logprobs in the include parameter to receive logprobs.

必填范围: 0 <= x <= 20

top_p · number · 默认值: 1

Nucleus sampling parameter. The model considers tokens with top_p cumulative probability mass. For example, 0.1 means only the top 10% probability tokens are considered. We recommend adjusting either this or temperature, but not both.

必填范围: 0 <= x <= 1

truncation · enum<string> · 默认值: disabled

The truncation strategy for handling inputs that exceed the model's context window.

• auto: The model truncates the input by dropping items from the beginning of the conversation to fit.
• disabled (default): The request fails with a 400 error if the input exceeds the context window.

可用选项: auto, disabled

user · string · 已弃用

Deprecated. Use safety_identifier and prompt_cache_key instead. A stable identifier for your end-user.

响应

200 - application/json

The generated Response object.

id · string

Unique identifier for the response.

示例:

"resp_0a153ae8201f73bc0069a7e8044cc481"

object · enum<string>

The object type, always response.

可用选项: response

示例:

"response"

created_at · integer

Unix timestamp (in seconds) of when the response was created.

示例:

1772611588

status · enum<string>

The status of the response.

可用选项: completed, in_progress, failed, cancelled, queued

示例:

"completed"

background · boolean

Whether the response was run in the background.

示例:

false

completed_at · integer | null

Unix timestamp of when the response was completed, or null if still in progress.

示例:

1772611589

error · object

Error information if the response failed, or null on success.

Show child attributes

incomplete_details · object

Details about why the response is incomplete, if applicable.

Show child attributes

instructions · string | null

The system instructions used for this response.

max_output_tokens · integer | null

The maximum output token limit that was applied.

model · string

The model used for the response.

示例:

"gpt-4.1-nano"

output · object[]

An array of output items generated by the model. Each item can be a message, function call, or other output type.

Show child attributes

output_text · string

A convenience field containing the concatenated text output from all output message items.

parallel_tool_calls · boolean

Whether parallel tool calls were enabled.

previous_response_id · string | null

The ID of the previous response, if this is a multi-turn conversation.

reasoning · object

The reasoning configuration that was used.

Show child attributes

service_tier · string

The service tier actually used to process the request.

示例:

"default"

store · boolean

Whether the response was stored.

temperature · number

The temperature value used.

示例:

1

text · object

The text configuration used.

Show child attributes

tool_choice · string object

The tool choice setting used.

tools · object[]

The tools that were available for this response.

top_p · number

The top_p value used.

示例:

1

truncation · string

The truncation strategy used.

usage · object

Token usage statistics for this response.

Show child attributes

user · string | null

The user identifier, if provided.

metadata · object

The metadata attached to this response.

Show child attributes

content_filters · array | null

Content filter results applied to the response, if any.

frequency_penalty · number · 默认值: 0

The frequency penalty applied to the request.

max_tool_calls · integer | null

Maximum number of tool calls allowed, if set.

presence_penalty · number · 默认值: 0

The presence penalty applied to the request.

prompt_cache_key · string | null

Cache key for prompt caching, if applicable.

prompt_cache_retention · string | null

Prompt cache retention policy, if applicable.

safety_identifier · string | null

Safety system identifier for the response, if applicable.

top_logprobs · integer · 默认值: 0

Number of top log probabilities returned per token position.