Skip to main content
POST
/
chat
/
tasks
curl --request POST \ --url https://app.nextbrowser.com/api/v1/chat/tasks \ --header 'Authorization: <api-key>' \ --header 'Content-Type: application/json' \ --data ' { "task_description": "Search for the latest news about artificial intelligence and summarize the top 3 articles", "llm_model": "gemini-2.0-flash", "proxy_settings": { "country": "US", "region": "California", "proxy_type": "residential" }, "browser_settings": { "browser_type": "persistent", "os_type": "linux" } } '
{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "chat_session_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "chat_title": "<string>",
  "browser_instance_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "browser_id": "<string>",
  "user_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "created_at": "2023-11-07T05:31:56Z",
  "state": "processing",
  "task_description": "<string>",
  "llm_model": "<string>"
}

Authorizations

​
Authorization
string
header
required

API key in the format 'x-api-key '

Body

application/json
​
task_description
string
required

Description of the task to be performed

​
chat_session_id
string<uuid>

Optional UUID of an existing chat session

​
llm_model
string
default:gemini-2.0-flash

The LLM model to use for the task. Choose the best for you => gpt-4o, gpt-4o-mini, gpt-4.1, gpt-4.1-mini, gemini-2.0-flash, gemini-2.0-flash-lite

​
proxy_settings
object

Proxy settings for the browser. Set up your automation with geolocation awareness, bypassing restrictions

​
browser_settings
object

Browser settings

Response

Task created successfully

​
id
string<uuid>

The UUID of the created task

​
chat_session_id
string<uuid>

The UUID of the associated chat session

​
chat_title
string

The title of the chat session

​
browser_instance_id
string<uuid>

The UUID of the browser instance

​
browser_id
string

The id of the browser connection

​
user_id
string<uuid>

The UUID of the user

​
created_at
string<date-time>

Timestamp when the task was created

​
state
enum<string>
default:processing

The current state of the task

Available options:
processing,
completed,
failed
​
task_description
string

The task description

​
llm_model
string

The LLM model used for the task