跳转到主要内容
POST
/
v1
/
chat
/
completions
Chat Completions
curl --request POST \
  --url https://api.apiyi.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello, please introduce yourself."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1000
}
'
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1702855400,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm an AI assistant, happy to help you. I can answer questions, write content, write code, and more. How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 42,
    "total_tokens": 67
  }
}

授权

​
Authorization
string
header
必填

API Key obtained from the APIYI Console

请求体

application/json
​
model
string
必填

Model name. APIYI supports 200+ models — just change the model name to switch between providers.

示例:

"gpt-4o"

"gpt-4o-mini"

"gpt-5-chat-latest"

"claude-sonnet-4-20250514"

"claude-opus-4-1-20250805"

"claude-3-5-haiku-20241022"

"gemini-2.5-pro"

"gemini-2.5-flash"

"gemini-2.0-flash"

"deepseek-r1"

"deepseek-v3-0324"

"grok-4-0709"

"grok-3"

"o4-mini"

"o3"

"qwen-max"

"glm-4-plus"

​
messages
object[]
必填

Array of conversation messages, supports multi-turn dialogue

示例:
[
  {
    "role": "system",
    "content": "You are a helpful assistant."
  },
  {
    "role": "user",
    "content": "Hello, please introduce yourself."
  }
]
​
temperature
number
默认值:1

Sampling temperature. Higher values (e.g., 0.8) make output more random, lower values (e.g., 0.2) make it more deterministic.

必填范围: 0 <= x <= 2
​
max_tokens
integer

Maximum number of tokens to generate. Different models have different limits.

必填范围: x >= 1
​
top_p
number
默认值:1

Nucleus sampling parameter. It is generally recommended not to modify both temperature and top_p.

必填范围: 0 <= x <= 1
​
n
integer
默认值:1

Number of completions to generate for each message.

必填范围: x >= 1
​
stream
boolean
默认值:false

Whether to stream results. The Playground does not support streaming preview — use an SDK to test.

​
stop

Stop sequence(s). Generation stops when this sequence is encountered. Up to 4.

​
presence_penalty
number
默认值:0

Presence penalty. Positive values increase the likelihood of talking about new topics.

必填范围: -2 <= x <= 2
​
frequency_penalty
number
默认值:0

Frequency penalty. Positive values decrease the likelihood of repeating the same text verbatim.

必填范围: -2 <= x <= 2
​
user
string

A unique identifier for the end user, used for monitoring and abuse detection.

响应

Successfully returned chat completion result

​
id
string

Unique identifier for the request

示例:

"chatcmpl-abc123"

​
object
enum<string>
可用选项:
chat.completion
示例:

"chat.completion"

​
created
integer

Creation timestamp (Unix seconds)

示例:

1702855400

​
model
string

The model actually used

示例:

"gpt-4o"

​
choices
object[]
​
usage
object

Token usage statistics