跳转到主要内容

Documentation Index

Fetch the complete documentation index at: https://docs.metask.ai/llms.txt

Use this file to discover all available pages before exploring further.

The chat completions endpoint is the primary way to interact with AI models through the gateway. You send a conversation — a list of messages with roles — and the model returns its reply. The endpoint is fully compatible with the OpenAI chat completions API, so any code written for OpenAI works here by changing only the base URL.

​
Endpoint

POST https://napi.origintask.cn/v1/chat/completions

​
Request parameters

​
model
string
必填
The ID of the model to use for this request. Use the GET /v1/models endpoint to retrieve the list of available model IDs.Example: "gpt-4o-mini"
​
messages
object[]
必填
An array of message objects representing the conversation history. Messages are processed in order.
​
stream
boolean
默认值:"false"
When true, the response is sent as a stream of server-sent events (SSE) rather than a single JSON object. Each event contains a partial completion delta. The stream ends with a data: [DONE] event.
​
temperature
number
默认值:"1"
Sampling temperature between 0 and 2. Lower values produce more deterministic output; higher values produce more varied output. Values above 1.5 can lead to incoherent responses.
​
max_tokens
integer
The maximum number of tokens to generate in the completion. When omitted, the model uses its default context limit. Setting this lower helps control costs.
​
top_p
number
默认值:"1"
Nucleus sampling parameter between 0 and 1. The model considers only the tokens comprising the top top_p probability mass. Use either temperature or top_p, not both.

​
Response fields

​
id
string
A unique identifier for this completion, prefixed with chatcmpl-.
​
object
string
Always "chat.completion" for non-streaming responses.
​
created
integer
Unix timestamp (seconds) of when the completion was created.
​
model
string
The model ID that was used to generate this completion.
​
choices
object[]
An array of completion choices. Most requests return a single choice at index 0.
​
usage
object
Token usage for this request.

​
Examples

curl https://napi.origintask.cn/v1/chat/completions \
  --request POST \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "What is the capital of France?" }
    ]
  }'

​
Streaming

Set stream: true to receive the response as a series of server-sent events. Each event carries a delta with the next chunk of text. This is useful for displaying output to users in real time. 
curl https://napi.origintask.cn/v1/chat/completions \
  --request POST \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "gpt-4o-mini",
    "stream": true,
    "messages": [
      { "role": "user", "content": "Tell me a short joke." }
    ]
  }'

​
Example response

{
  "id": "chatcmpl-abc123xyz",
  "object": "chat.completion",
  "created": 1744416000,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 9,
    "total_tokens": 33
  }
}