主题切换
创建聊天补全 deepseek v3.1思考程度 (流式）
OpenAPI Specification
yaml
openapi: 3.0.1
info:
title: ''
description: ''
version: 1.0.0
paths:
/v1/chat/completions:
post:
summary: 创建聊天补全 deepseek v3.1思考程度 (流式）
deprecated: false
description: ''
tags:
- 聊天(Chat)/ChatGPT聊天（Chat）
parameters:
- name: Content-Type
in: header
description: ''
required: true
example: application/json
schema:
type: string
- name: Accept
in: header
description: ''
required: true
example: application/json
schema:
type: string
- name: Authorization
in: header
description: ''
required: false
example: Bearer {{YOUR_API_KEY}}
schema:
type: string
- name: X-Forwarded-Host
in: header
description: ''
required: false
example: localhost:5173
schema:
type: string
requestBody:
content:
application/json:
schema:
type: object
properties:
model:
type: string
description: 使用的模型的 ID。
max_tokens:
type: integer
description: >-
限制一次请求中模型生成 completion 的最大 token 数。输入 token 和输出 token
的总长度受模型的上下文长度的限制。
messages:
type: array
items:
type: object
properties:
role:
type: string
content:
type: string
required:
- role
- content
x-apifox-orders:
- role
- content
description: 对话的消息列表。
temperature:
type: integer
description: >-
使用什么采样温度，介于 0 和 2 之间。较高的值（如 0.8）将使输出更加随机，而较低的值（如
0.2）将使输出更加集中和确定。
stream:
type: boolean
description: >-
如果设置为 True，将会以 SSE（server-sent events）的形式以流式发送消息增量。消息流以
data: [DONE] 结尾。
stream_options:
type: object
properties:
include_usage:
type: boolean
description: >-
如果设置为 true，在流式消息最后的 data: [DONE] 之前将会传输一个额外的块。此块上的 usage
字段显示整个请求的 token 使用统计信息，而 choices 字段将始终是一个空数组。所有其他块也将包含一个
usage 字段，但其值为 null。
x-apifox-orders:
- include_usage
description: 流式输出相关选项。只有在 stream 参数为 true 时，才可设置此参数。
thinking:
type: object
properties:
type:
type: string
description: |-
enabled：默认强制开启，强制开启深度思考能力。
disabled：强制关闭深度思考能力。
auto：模型自行判断是否进行深度思考。
x-apifox-orders:
- type
description: 部分深度思考能力的模型支持通过 thinking 字段控制是否关闭深度思考能力。
required:
- model
- messages
x-apifox-orders:
- model
- max_tokens
- messages
- temperature
- stream
- stream_options
- thinking
example:
model: deepseek-v3-1-250821
max_tokens: 1000
messages:
- role: system
content: You are a helpful assistant.
- role: user
content: 你好
temperature: 1
stream: true
stream_options:
include_usage: true
thinking:
type: enabled
responses:
'200':
description: ''
content:
application/json:
schema:
type: object
properties:
id:
type: string
object:
type: string
created:
type: integer
choices:
type: array
items:
type: object
properties:
index:
type: integer
message:
type: object
properties:
role:
type: string
content:
type: string
required:
- role
- content
x-apifox-orders:
- role
- content
finish_reason:
type: string
x-apifox-orders:
- index
- message
- finish_reason
usage:
type: object
properties:
prompt_tokens:
type: integer
completion_tokens:
type: integer
total_tokens:
type: integer
required:
- prompt_tokens
- completion_tokens
- total_tokens
x-apifox-orders:
- prompt_tokens
- completion_tokens
- total_tokens
required:
- id
- object
- created
- choices
- usage
x-apifox-orders:
- id
- object
- created
- choices
- usage
example:
id: chatcmpl-123
object: chat.completion
created: 1677652288
choices:
- index: 0
message:
role: assistant
content: |-
Hello there, how may I assist you today?
finish_reason: stop
usage:
prompt_tokens: 9
completion_tokens: 12
total_tokens: 21
headers: {}
x-apifox-name: OK
security:
- bearer: []
x-apifox-folder: 聊天(Chat)/ChatGPT聊天（Chat）
x-apifox-status: released
x-run-in-apifox: https://app.apifox.com/web/project/7937429/apis/api-427877229-run
components:
schemas: {}
securitySchemes:
bearer:
type: http
scheme: bearer
servers:
- url: https://new.22codex.xyz
description: 正式环境
security:
- bearer: []