Skip to main content
POST
/
chat
/
completions
Chat / LLM completion
curl --request POST \
  --url https://api.runcrate.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>",
      "name": "<string>"
    }
  ],
  "max_tokens": 2,
  "temperature": 1,
  "top_p": 0.5,
  "stop": "<string>",
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "stream": false,
  "tools": [
    {}
  ],
  "tool_choice": "<string>",
  "response_format": {}
}
'
import requests

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

payload = {
    "model": "<string>",
    "messages": [
        {
            "content": "<string>",
            "name": "<string>"
        }
    ],
    "max_tokens": 2,
    "temperature": 1,
    "top_p": 0.5,
    "stop": "<string>",
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "stream": False,
    "tools": [{}],
    "tool_choice": "<string>",
    "response_format": {}
}
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: '<string>',
    messages: [{content: '<string>', name: '<string>'}],
    max_tokens: 2,
    temperature: 1,
    top_p: 0.5,
    stop: '<string>',
    frequency_penalty: 0,
    presence_penalty: 0,
    stream: false,
    tools: [{}],
    tool_choice: '<string>',
    response_format: {}
  })
};

fetch('https://api.runcrate.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.runcrate.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' => [
        [
                'content' => '<string>',
                'name' => '<string>'
        ]
    ],
    'max_tokens' => 2,
    'temperature' => 1,
    'top_p' => 0.5,
    'stop' => '<string>',
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'stream' => false,
    'tools' => [
        [
                
        ]
    ],
    'tool_choice' => '<string>',
    'response_format' => [
        
    ]
  ]),
  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.runcrate.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"max_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"stream\": false,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {}\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.runcrate.ai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"max_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"stream\": false,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {}\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://api.runcrate.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\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\"\n    }\n  ],\n  \"max_tokens\": 2,\n  \"temperature\": 1,\n  \"top_p\": 0.5,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"stream\": false,\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {}\n}"

response = http.request(request)
puts response.read_body
{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "content": "<string>",
        "name": "<string>"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}
{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "details": {}
  }
}
{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "details": {}
  }
}
{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "details": {}
  }
}

Authorizations

Authorization
string
header
required

Use a Runcrate API key with the rc_live_* prefix as the bearer token. Create one at https://www.runcrate.ai/dashboard/api-keys.

Body

application/json
model
string
required

Model id from the catalog (e.g. deepseek/deepseek-v3.2).

messages
object[]
required
max_tokens
integer
Required range: x >= 1
temperature
number
Required range: 0 <= x <= 2
top_p
number
Required range: 0 <= x <= 1
stop
frequency_penalty
number
Required range: -2 <= x <= 2
presence_penalty
number
Required range: -2 <= x <= 2
stream
boolean
default:false
tools
object[]
tool_choice
response_format
object

Response

Completion (or SSE stream when stream=true).

id
string
object
enum<string>
Available options:
chat.completion
created
integer
model
string
choices
object[]
usage
object