Chat Completions 格式

根據對話歷史建立模型響應。支援流式和非流式輸出。

相容 OpenAI Chat Completions API。

POST /v1/chat/completions https://api.covanexus.com

Authorization

內容

Authorization

Authorization BearerAuth

Authorization Bearer <token>

使用 Bearer Token 認證。格式：Authorization: Bearer $COVA_NEXUS_API_KEY

in: 標頭

請求內容

application/json

model* string

模型識別碼

messages* array[object]

對話訊息列表

temperature? number

取樣溫度

Default 1 | Range 0 ≤ value ≤ 2

top_p? number

核取樣引數

Default 1 | Range 0 ≤ value ≤ 1

n? integer

生成數量

Default 1 ≥ value

stream? boolean

是否流式輸出

Default false

stream_options? object

流式輸出選項

stop? string | array[string]

停止字串

max_tokens? integer

最大生成 Token 數

max_completion_tokens? integer

最大補全 Token 數

presence_penalty? number

存在懲罰

Default 0 | Range -2 ≤ value ≤ 2

frequency_penalty? number

頻率懲罰

Default 0 | Range -2 ≤ value ≤ 2

logit_bias? object

詞元偏置

user? string

使用者標識

tools? array[object]

可用工具清單（Function Calling）

tool_choice? string | object

工具選擇策略

response_format? object

響應格式

seed? integer

隨機種子

reasoning_effort? string

推理強度（用於支援推理的模型）

Value in "low" | "medium" | "high"

modalities? array[string]

輸出模態

audio? object

音訊輸出設定

回應內容

狀態碼	型別
200	application/json
400	application/json
429	application/json

curl -X POST "https://api.covanexus.com/v1/chat/completions" \
  -H "Authorization: Bearer " \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-4",
  "messages": [
    {
      "role": "system",
      "content": "string"
    },
    {
      "role": "user",
      "content": "string"
    }
  ]
}'

const response = await fetch(
  "https://api.covanexus.com/v1/chat/completions",
  {
    method: "POST",
    headers: {
      "Authorization": "Bearer ",
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      model: "gpt-4",
      messages: [
        { role: "user", content: "string" }
      ]
    })
  }
);

package main

import (
  "bytes"
  "net/http"
)

func main() {
  body := []byte(`{
    "model": "gpt-4",
    "messages": [
      {"role": "user", "content": "string"}
    ]
  }`)
  req, _ := http.NewRequest("POST",
    "https://api.covanexus.com/v1/chat/completions",
    bytes.NewBuffer(body))
  req.Header.Set("Authorization", "Bearer ")
  req.Header.Set("Content-Type", "application/json")
  http.DefaultClient.Do(req)
}

from openai import OpenAI

client = OpenAI(
    api_key="$COVA_NEXUS_API_KEY",
    base_url="https://api.covanexus.com/v1"
)
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "user", "content": "string"}
    ]
)

HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.covanexus.com/v1/chat/completions"))
    .header("Authorization", "Bearer ")
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString(
        "{\"model\":\"gpt-4\",\"messages\":[{\"role\":\"user\",\"content\":\"string\"}]}"
    )).build();

var client = new HttpClient();
client.DefaultRequestHeaders.Add(
    "Authorization", "Bearer ");
var content = new StringContent(
    "{\"model\":\"gpt-4\",\"messages\":[{\"role\":\"user\",\"content\":\"string\"}]}",
    Encoding.UTF8, "application/json");
var response = await client.PostAsync(
    "https://api.covanexus.com/v1/chat/completions",
    content);

200

400

429

{
  "id": "string",
  "object": "chat.completion",
  "created": 0,
  "model": "string",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "system",
        "content": "string"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  }
}

BearerAuth