建立模型回應

POST

responses

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key=os.environ["COMETAPI_KEY"],
)

response = client.responses.create(
    model="gpt-5.6-sol",
    input="Tell me a three sentence bedtime story about a unicorn.",
)

print(response.output_text)

{
  "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": {}
}

回應 API 擴充了聊天補全，支援有狀態對話、內建工具、多模態檔案輸入及推論控制。這是 OpenAI o-series 推論模型、GPT-5 系列及 Codex 模型的建議端點。

不同模型供應商支援不同的請求參數，並傳回不同的回應欄位。上方 playground 所列的參數並非全都能搭配 CometAPI 上的每個模型使用。

使用有狀態對話

使用 previous_response_id 串連回應，而非自行管理訊息歷程：

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key=os.environ["COMETAPI_KEY"],
)

# First turn
response = client.responses.create(
    model="gpt-5.6-sol",
    input="What is quantum computing?",
)

# Second turn — previous context is included automatically
follow_up = client.responses.create(
    model="gpt-5.6-sol",
    input="Can you explain that more simply?",
    previous_response_id=response.id,
)

print(follow_up.output_text)

使用內建工具

回應 API 包含無需設定的平台提供工具：

工具	用途
`web_search_preview`	搜尋網路以取得即時資訊
`file_search`	搜尋已上傳的檔案
`code_interpreter`	在沙箱中執行 Python 程式碼

若要啟用內建工具，請將其加入 tools 陣列：

response = client.responses.create(
    model="gpt-5.6-sol",
    input="Find the current price of Bitcoin",
    tools=[{"type": "web_search_preview"}],
)

print(response.output_text)

呼叫自訂函式

定義模型可透過結構化引數呼叫的函式：

response = client.responses.create(
    model="gpt-5.6-sol",
    input="What's the weather in Tokyo?",
    tools=[{
        "type": "function",
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            },
            "required": ["location"]
        }
    }],
)

當模型呼叫函式時，回應的 output 陣列會包含一個 function_call 項目，其中含有函式名稱及已剖析的引數。執行該函式，並在後續請求中傳回結果。

請求結構化輸出

若要強制輸出符合特定 schema 的 JSON，請使用 text.format 參數：

response = client.responses.create(
    model="gpt-5.6-sol",
    input="List 3 programming languages with their main use cases",
    text={
        "format": {
            "type": "json_schema",
            "name": "languages",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {
                    "languages": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "name": {"type": "string"},
                                "use_case": {"type": "string"}
                            },
                            "required": ["name", "use_case"],
                            "additionalProperties": False
                        }
                    }
                },
                "required": ["languages"],
                "additionalProperties": False
            }
        }
    },
)

設定推論

對於 o-series 和 GPT-5 模型，請使用 reasoning.effort 控制推論深度：

response = client.responses.create(
    model="o3",
    input="Solve this step by step: if f(x) = x^3 - 6x^2 + 11x - 6, find all roots.",
    reasoning={"effort": "high"},  # "low", "medium", or "high"
)

print(response.output_text)

較高的推論投入程度可產生更周全的答案，但會使用更多 Token。簡單查詢請使用 "low"，複雜的多步驟問題請使用 "high"。

串流（Streaming）回應

若要接收增量輸出，請將 stream 設為 true。API 會依下列順序傳送伺服器傳送事件（SSE）：

response.created — 回應物件已初始化
response.in_progress — 已開始產生內容
response.output_item.added — 新增輸出項目（訊息或工具呼叫)
response.content_part.added — 內容部分已開始
response.output_text.delta — 文字區塊（包含 delta 欄位)
response.output_text.done — 此內容部分的文字產生完成
response.content_part.done — 內容部分已完成
response.output_item.done — 輸出項目已完成
response.completed — 包含 usage 資料的完整回應

使用 Python SDK 串流回應：

stream = client.responses.create(
    model="gpt-5.6-sol",
    input="Write a haiku about coding",
    stream=True,
)

for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="")

如需各項功能的深入指南，請參閱 OpenAI 文件：文字 · 圖片 · PDF 檔案 · 結構化輸出 · 函式呼叫（Function Calling） · 對話狀態 · 內建工具 · 推論

授權

Authorization

string

header

必填

Bearer token authentication. Use your CometAPI key.

主體

application/json

model

string

必填

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

範例:

"gpt-5.6-sol"

input

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

預設值: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

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.

可用選項:

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

預設值: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.

可用選項:

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.

可用選項:

auto,

default,

flex,

priority

store

boolean

預設值:true

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

stream

boolean

預設值: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

預設值: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.

必填範圍: 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

預設值: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.

必填範圍: 0 <= x <= 20

top_p

number

預設值: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.

必填範圍: 0 <= x <= 1

truncation

enum<string>

預設值: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.

可用選項:

auto,

disabled

user

string

已棄用

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

回應

200 - application/json

The generated Response object.

string

Unique identifier for the response.

範例:

"resp_0a153ae8201f73bc0069a7e8044cc481"

object

enum<string>

The object type, always response.

可用選項:

response

範例:

"response"

created_at

integer

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

範例:

1772611588

status

enum<string>

The status of the response.

可用選項:

completed,

in_progress,

failed,

cancelled,

queued

範例:

"completed"

background

boolean

Whether the response was run in the background.

範例:

false

completed_at

integer | null

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

範例:

1772611589

error

object | null

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

Show child attributes

incomplete_details

object | null

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.

範例:

"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.

範例:

"default"

store

boolean

Whether the response was stored.

temperature

number

The temperature value used.

範例:

1

text

object

The text configuration used.

Show child attributes

tool_choice

The tool choice setting used.

tools

object[]

The tools that were available for this response.

top_p

number

The top_p value used.

範例:

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

預設值:0

The frequency penalty applied to the request.

max_tool_calls

integer | null

Maximum number of tool calls allowed, if set.

presence_penalty

number

預設值: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

預設值:0

Number of top log probabilities returned per token position.

建立聊天補全

建立訊息

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key=os.environ["COMETAPI_KEY"],
)

response = client.responses.create(
    model="gpt-5.6-sol",
    input="Tell me a three sentence bedtime story about a unicorn.",
)

print(response.output_text)

{
  "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": {}
}

內容審核

API 金鑰

使用有狀態對話

使用內建工具

呼叫自訂函式

請求結構化輸出

設定推論

串流（Streaming）回應

授權

主體

回應

​使用有狀態對話

​使用內建工具

​呼叫自訂函式

​請求結構化輸出

​設定推論

​串流（Streaming）回應

授權

主體

回應

使用有狀態對話

使用內建工具

呼叫自訂函式

請求結構化輸出

設定推論

串流（Streaming）回應