Chat Completions

POST

chat

completions

Chat Completions

curl --request POST \
  --url https://api.derestricted.ai/v1/chat/completions \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": true,
  "max_tokens": 123,
  "stream_options": {},
  "tools": [
    {}
  ]
}
'

import requests

url = "https://api.derestricted.ai/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "stream": True,
    "max_tokens": 123,
    "stream_options": {},
    "tools": [{}]
}
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

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

print(response.text)

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

fetch('https://api.derestricted.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.derestricted.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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'stream' => true,
    'max_tokens' => 123,
    'stream_options' => [
        
    ],
    'tools' => [
        [
                
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "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.derestricted.ai/v1/chat/completions"

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

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

	req.Header.Add("Authorization", "<authorization>")
	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.derestricted.ai/v1/chat/completions")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"max_tokens\": 123,\n  \"stream_options\": {},\n  \"tools\": [\n    {}\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.derestricted.ai/v1/chat/completions")

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

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

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

Send the messages needed for the current turn. Conversation history is supplied by your application on every request.

string

required

Bearer followed by your derestricted API key.

string

default:"derestricted-llm"

Use derestricted-llm. Omitting this field uses the same deployment.

array

required

Conversation messages, such as {"role": "user", "content": "Hello"}. Include prior assistant messages and tool results when continuing a conversation. Maximum 2,000 items.

boolean

default:"false"

Set to true for server-sent events.

integer

Output allowance, capped at 65,536. If omitted, the service chooses an affordable allowance up to 32,768. max_completion_tokens is also accepted and takes precedence when both fields are present.

object

With streaming, use {"include_usage": true} to request the final usage chunk.

array

Optional client-defined tool schemas. Your application executes calls and returns their results. Up to 128 tool definitions are accepted within the shared request limits.

Example

curl https://api.derestricted.ai/v1/chat/completions \
  -H "Authorization: Bearer $DERESTRICTED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "derestricted-llm",
    "messages": [
      {"role": "system", "content": "Answer concisely."},
      {"role": "user", "content": "When should I use a queue instead of a direct function call?"}
    ],
    "max_tokens": 8192
  }'

Read answer text from choices[0].message.content. A response can also contain message.tool_calls or a message.reasoning_content extension. Check finish_reason; reaching the output limit may leave the answer incomplete.

Streaming

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.derestricted.ai/v1",
    api_key=os.environ["DERESTRICTED_API_KEY"],
)

with client.chat.completions.create(
    model="derestricted-llm",
    messages=[{"role": "user", "content": "Explain eventual consistency briefly."}],
    max_tokens=8192,
    stream=True,
    stream_options={"include_usage": True},
) as stream:
    for chunk in stream:
        if chunk.choices:
            text = chunk.choices[0].delta.content
            if text:
                print(text, end="", flush=True)
        if chunk.usage:
            print("\nUsage:", chunk.usage)

Raw SSE clients receive JSON in data: frames followed by data: [DONE]. Keepalive comments such as : ping contain no generated text. Answer text arrives in choices[].delta.content; reasoning may arrive separately in delta.reasoning_content or delta.reasoning. When usage is requested, the final usage chunk may have an empty choices array. Do not assume every chunk contains a choice. An error frame can occur after HTTP 200; treat it as a failed generation even if some text has already arrived.

Tool calls

Supply function definitions using the Chat Completions tool shape. If the model returns a tool call, validate its arguments, execute the approved operation in your application, and send the assistant tool call plus a role: "tool" result with the matching tool_call_id in the next request. The API does not run functions or enforce a strict JSON Schema contract for arguments. See compatibility limits and errors.

⌘I

Chat Completions

curl --request POST \
  --url https://api.derestricted.ai/v1/chat/completions \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": true,
  "max_tokens": 123,
  "stream_options": {},
  "tools": [
    {}
  ]
}
'

import requests

url = "https://api.derestricted.ai/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "stream": True,
    "max_tokens": 123,
    "stream_options": {},
    "tools": [{}]
}
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

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

print(response.text)

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

fetch('https://api.derestricted.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.derestricted.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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'stream' => true,
    'max_tokens' => 123,
    'stream_options' => [
        
    ],
    'tools' => [
        [
                
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "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.derestricted.ai/v1/chat/completions"

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

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

	req.Header.Add("Authorization", "<authorization>")
	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.derestricted.ai/v1/chat/completions")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"stream\": true,\n  \"max_tokens\": 123,\n  \"stream_options\": {},\n  \"tools\": [\n    {}\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.derestricted.ai/v1/chat/completions")

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

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

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

Overview

Endpoints

Troubleshooting

Example

Streaming

Tool calls

​Example

​Streaming

​Tool calls

Example

Streaming

Tool calls