Chat Completions

POST

chat

completions

Chat Completions

curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": true,
  "temperature": 123,
  "max_tokens": 123,
  "top_p": 123,
  "stop": {}
}
'

import requests

url = "https://api.example.com/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "stream": True,
    "temperature": 123,
    "max_tokens": 123,
    "top_p": 123,
    "stop": {}
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [{}],
    stream: true,
    temperature: 123,
    max_tokens: 123,
    top_p: 123,
    stop: {}
  })
};

fetch('https://api.example.com/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.example.com/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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'stream' => true,
    'temperature' => 123,
    'max_tokens' => 123,
    'top_p' => 123,
    'stop' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "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.example.com/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"stop\": {}\n}")

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

	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.example.com/v1/chat/completions")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"stop\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"stop\": {}\n}"

response = http.request(request)
puts response.read_body

Create Chat Completion

Generate a response from an AI model given a conversation history.

Request

POST https://api.modelstack.cc/v1/chat/completions

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer your_api_key`
`Content-Type`	Yes	`application/json`

Body Parameters

string

required

The model ID to use (e.g., claude-sonnet-4-5, gpt-4o, gemini-2.5-pro). See Supported Models for the full list.

array

required

An array of message objects representing the conversation history.Each message object has:

role (string): One of system, user, or assistant
content (string): The message content

boolean

default:"false"

If true, responses are streamed back as Server-Sent Events (SSE).

number

default:"1.0"

Sampling temperature between 0 and 2. Lower values make output more focused and deterministic.

integer

Maximum number of tokens to generate in the response.

number

default:"1.0"

Nucleus sampling parameter. An alternative to temperature.

string | array

Up to 4 sequences where the API will stop generating further tokens.

Example Request

curl https://api.modelstack.cc/v1/chat/completions \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

from openai import OpenAI

client = OpenAI(
    api_key="your_api_key",
    base_url="https://api.modelstack.cc/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    temperature=0.7,
    max_tokens=500
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your_api_key",
  baseURL: "https://api.modelstack.cc/v1",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain quantum computing in simple terms." },
  ],
  temperature: 0.7,
  max_tokens: 500,
});

console.log(response.choices[0].message.content);

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699000000,
  "model": "claude-sonnet-4-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses quantum bits (qubits) instead of classical bits..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Response Fields

Field	Type	Description
`id`	string	Unique identifier for the completion
`object`	string	Always `chat.completion`
`created`	integer	Unix timestamp of creation
`model`	string	The model used
`choices`	array	Array of completion choices
`choices[].message`	object	The generated message
`choices[].finish_reason`	string	`stop`, `length`, or `content_filter`
`usage`	object	Token usage statistics

Streaming

Set "stream": true to receive Server-Sent Events (SSE) as the model generates tokens.

Streaming Request

curl https://api.modelstack.cc/v1/chat/completions \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "Write a haiku about coding."}],
    "stream": true
  }'

Streaming Response

Each event is a JSON object prefixed with data: :

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Lines"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" of"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" code"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Streaming with Python

stream = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Write a haiku about coding."}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

Streaming with Node.js

const stream = await client.chat.completions.create({
  model: "claude-sonnet-4-5",
  messages: [{ role: "user", content: "Write a haiku about coding." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Chat Completions

curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": true,
  "temperature": 123,
  "max_tokens": 123,
  "top_p": 123,
  "stop": {}
}
'

import requests

url = "https://api.example.com/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "stream": True,
    "temperature": 123,
    "max_tokens": 123,
    "top_p": 123,
    "stop": {}
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [{}],
    stream: true,
    temperature: 123,
    max_tokens: 123,
    top_p: 123,
    stop: {}
  })
};

fetch('https://api.example.com/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.example.com/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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'stream' => true,
    'temperature' => 123,
    'max_tokens' => 123,
    'top_p' => 123,
    'stop' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "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.example.com/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"stop\": {}\n}")

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

	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.example.com/v1/chat/completions")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"stop\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"temperature\": 123,\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"stop\": {}\n}"

response = http.request(request)
puts response.read_body

Overview

Endpoints

Create Chat Completion

Request

Headers

Body Parameters

Example Request

Response

Response Fields

Streaming

Streaming Request

Streaming Response

Streaming with Python

Streaming with Node.js

​Create Chat Completion

​Request

​Headers

​Body Parameters

​Example Request

​Response

​Response Fields

​Streaming

​Streaming Request

​Streaming Response

​Streaming with Python

​Streaming with Node.js

Create Chat Completion

Request

Headers

Body Parameters

Example Request

Response

Response Fields

Streaming

Streaming Request

Streaming Response

Streaming with Python

Streaming with Node.js