Skip to main content
POST
/
v1
/
chat
/
completions
OpenAI chat completions
curl --request POST \
  --url https://api-vip.apigo.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "temperature": 0.7,
  "stream": true
}
'
import requests

url = "https://api-vip.apigo.ai/v1/chat/completions"

payload = {
"model": "gpt-4o",
"messages": [{ "content": "<string>" }],
"temperature": 0.7,
"stream": True
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: 'gpt-4o',
messages: [{content: '<string>'}],
temperature: 0.7,
stream: true
})
};

fetch('https://api-vip.apigo.ai/v1/chat/completions', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
CURLOPT_URL => "https://api-vip.apigo.ai/v1/chat/completions",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'model' => 'gpt-4o',
'messages' => [
[
'content' => '<string>'
]
],
'temperature' => 0.7,
'stream' => true
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}
package main

import (
"fmt"
"strings"
"net/http"
"io"
)

func main() {

url := "https://api-vip.apigo.ai/v1/chat/completions"

payload := strings.NewReader("{\n \"model\": \"gpt-4o\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"temperature\": 0.7,\n \"stream\": true\n}")

req, _ := http.NewRequest("POST", url, payload)

req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")

res, _ := http.DefaultClient.Do(req)

defer res.Body.Close()
body, _ := io.ReadAll(res.Body)

fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://api-vip.apigo.ai/v1/chat/completions")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"model\": \"gpt-4o\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"temperature\": 0.7,\n \"stream\": true\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api-vip.apigo.ai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"model\": \"gpt-4o\",\n \"messages\": [\n {\n \"content\": \"<string>\"\n }\n ],\n \"temperature\": 0.7,\n \"stream\": true\n}"

response = http.request(request)
puts response.read_body
{
  "id": "<string>",
  "object": "chat.completion",
  "choices": [
    {
      "index": 123,
      "message": {
        "content": "<string>"
      },
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}
{
"error": 123,
"message": "<string>"
}
Creates a model response for a chat conversation. This endpoint is still the safest default when you need compatibility with existing OpenAI SDKs, chat clients, or legacy chat-completion workflows. Supported fields vary by model, especially for reasoning, tool use, and multimodal inputs.

Integration guidance

  • Authenticate with Authorization: Bearer {API_KEY}
  • Use this as the default entry point for existing OpenAI-style chat integrations
  • If you want a more unified interface for structured output, multimodal input, and tools, prefer /v1/responses
  • Streaming clients should handle SSE chunks incrementally instead of waiting for one final JSON response

Request highlights

  • messages is required and carries the conversation history
  • model is required and selects the target model
  • temperature and top_p both affect sampling, but most integrations should tune only one of them
  • If you need token-level probabilities, combine logprobs with top_logprobs
  • For caching and safety attribution, prefer prompt_cache_key and safety_identifier

Response highlights

  • Plain text is usually read from choices[0].message.content
  • Tool calls can be read from message.tool_calls
  • Streaming responses arrive as SSE chunks and must be merged incrementally
  • Usage accounting is exposed through usage, including more detailed token breakdowns

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
string
required
Example:

"gpt-4o"

messages
object[]
required
temperature
number
Example:

0.7

stream
boolean

Response

Successful chat completion response

id
string
object
string
Example:

"chat.completion"

choices
object[]
usage
object