Skip to main content
POST
使用响应 API 通过 gpt-6-astra 发送文本、图像、文件和对话历史记录。示例还演示了网络搜索、自定义函数调用、结构化输出、推理和流式输出(Streaming)。
OpenAI 响应参考 介绍了完整的 API 格式;这里的示例针对 CometAPI 配置该格式。

继续对话

对于纯文本对话,请保留用户消息和助手的文本回复,然后添加下一条用户消息:
response.output_text 是一个 SDK 便捷属性,用于合并响应中的助手文本。函数调用(Function Calling)对话还需要保留其工具调用和结果项,如下所述。

使用网络搜索

添加 web_search 工具以搜索信息并包含来源引用:
当应用需要搜索结果或引用时,请检查返回的 web_search_call 项以及消息的 URL 注释。其他内置工具需要各自的配置;请参阅 OpenAI 工具指南.

调用自定义函数

定义函数参数,并让模型请求调用该函数:
函数调用会显示为一个 function_call 输出项。其 arguments 字段是一个 JSON 编码的字符串。执行你的函数,然后根据原始输入和返回的输出项构建下一个请求,但不包含这些输出项的响应项 id 字段。保留函数的 nameargumentscall_id,并追加一个 function_call_output 项,其中包含匹配的 call_id 以及位于 output 中的结果。

请求结构化输出

使用 text.format 请求符合 schema 的 JSON:
在解析 JSON 之前,请检查响应是否已完成且未拒绝该请求。达到输出 Token 限制的响应可能不完整。

配置推理

reasoning.effort 设置为相应值,以选择模型的推理强度:
这些示例对常规任务使用 low,对推理示例使用 highmax_output_tokens 同时包含推理 Token 和可见输出 Token。

流式传输响应

stream 设置为 true,以接收服务器发送的事件:
文本响应包含生命周期事件,例如 response.createdresponse.in_progressresponse.completed。文本会通过 response.output_text.delta 事件传入。工具和推理事件取决于请求,因此应根据事件的 type 进行处理,而不要假设每个响应都有相同的序列。
请参阅 OpenAI 关于以下内容的指南: 图像输入, 文件输入, 结构化输出, 函数调用(Function Calling), 对话状态,以及 推理.

授权

Authorization
string
header
必填

Bearer token authentication. Use your CometAPI key.

请求体

application/json
model
string
默认值:gpt-6-astra
必填

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

示例:

"gpt-6-astra"

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

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.

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.

parallel_tool_calls
boolean

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

previous_response_id
string

An ID for a stored response that is accessible to the selected model and request context. Cannot be combined with conversation. The conversation-history example sends prior input and output items explicitly.

prompt
object

Reference to a prompt template and its variables.

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>
已弃用

Legacy prompt-cache retention setting. Refer to the selected model documentation for prompt_cache_options and supported retention settings.

可用选项:
in_memory,
24h
reasoning
object

Reasoning configuration for the selected model.

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

Request response storage for later retrieval, when supported by the selected model and request context.

stream
boolean

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.

temperature
number

Sampling temperature. Omit this field for GPT-6 Astra.

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.

tool_choice

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[]

Tools available to the model. This page demonstrates web_search and custom function tools. Other tool types require their own configuration; see the official tool reference.

top_logprobs
integer

Number of token alternatives to include for models supporting log probabilities. Requires message.output_text.logprobs in include. Omit for GPT-6 Astra.

必填范围: 0 <= x <= 20
top_p
number

Nucleus sampling threshold. Omit this field for GPT-6 Astra. For sampling overrides, adjust either top_p or temperature.

必填范围: 0 <= x <= 1
truncation
enum<string>

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_example"

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:

1788763707

status
enum<string>

The status of the response.

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

1788763711

error
object | null

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

incomplete_details
object | null

Details about why the response is incomplete, if applicable.

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-6-astra"

output
object[]

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

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.

service_tier
string

The service tier actually used to process the request.

store
boolean

Whether the response was stored.

temperature
number

The temperature value used.

text
object

The text configuration used.

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.

truncation
string

The truncation strategy used.

usage
object

Token usage statistics for this response.

user
string | null

The user identifier, if provided.

metadata
object

The metadata attached to this response.

content_filters
array | null

Content filter results applied to the response, if any.

frequency_penalty
number

The frequency penalty applied to the request.

max_tool_calls
integer | null

Maximum number of tool calls allowed, if set.

presence_penalty
number

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

Number of top log probabilities returned per token position.

最后修改于 2026年9月8日