Browser Use Run

Browser Use Run

Certified

Run a Browser Use cloud agent

Gives a Browser Use cloud agent a task in plain language, waits until the run finishes, and returns its answer. The task creates a run, polls GET /runs/{id}/status until the run is completed, failed, or cancelled, then reads the full run once. A failed or cancelled run fails the task. If the task fails after the run is created, it cancels that run so the agent does not keep spending credits. The task returns the agent's result text. Ask for JSON in the prompt and parse it with fromJson. The task polls until the run ends, so set a task timeout or maxCostUsd to bound the time and the spend.

yaml
type: io.kestra.plugin.browseruse.Run

Check a price and parse the JSON answer

yaml
id: competitor_price_check
namespace: company.team

tasks:
  - id: check_price
    type: io.kestra.plugin.browseruse.Run
    apiKey: "{{ secret('BROWSER_USE_API_KEY') }}"
    prompt: >
      Open https://example.com/pricing, find the monthly price of the Pro plan
      and reply with only JSON like {"plan": "Pro", "price_eur": 49}.
    maxCostUsd: 1

  - id: log_price
    type: io.kestra.plugin.core.log.Log
    message: "Pro plan costs {{ fromJson(outputs.check_price.result).price_eur }} EUR"

Choose the model and the poll interval

yaml
id: browser_use_with_model
namespace: company.team

tasks:
  - id: check
    type: io.kestra.plugin.browseruse.Run
    apiKey: "{{ secret('BROWSER_USE_API_KEY') }}"
    model: gpt-5.6-luna
    pollInterval: PT15S
    prompt: Find the top story on https://news.ycombinator.com and reply with the title only.
Properties

Browser Use API key

API key sent in the X-Browser-Use-API-Key header. Create one at https://cloud.browser-use.com/settings?tab=api-keys.

Instructions for the browser agent

What the agent should do, in plain language. The value is sent as the API task field. Ask for JSON in the text if a later task needs structured fields.

Assets this task consumes as inputs or produces as outputs, for lineage tracking and the asset graph (Enterprise Edition). A flow declaring this property on a task is rejected in the open-source edition.

Definitions
assetFailureBehaviorstring
Possible Values
IGNOREFAILWARN

Asset failure behavior

Behavior applied to the task state when a declared asset fails to render, emit, or be persisted (e.g. a lock conflict): FAIL escalates it to FAILED, WARN (default) warns it if it would otherwise succeed, IGNORE leaves the state untouched.

enableAutobooleanstring

Whether to auto-register assets referenced dynamically at runtime that are not statically declared in inputs or outputs.

inputsarray

The assets consumed as inputs.

id*string
Min length1
typestring
outputs

The assets produced as outputs.

id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*object
descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
id*string
Min length1
Max length150
type*string
Min length1

Custom asset type

descriptionstring
displayNamestring
metadataobject
Default{}
namespacestring
Min length1
Max length150
Defaulthttps://api.browser-use.com/api/v4

API base URL

Browser Use API v4 base URL. Defaults to https://api.browser-use.com/api/v4.

Maximum cost in USD

Optional cap sent as maxCostUsd. Browser Use stops the run when the cap is reached. Must be greater than 0.

Model

Optional model id, for example gpt-6-luna. Leave empty to use Browser Use's current default. The model list changes, so this is a free string rather than a fixed set.

DefaultPT2S

Status poll interval

How long to wait between status reads. Defaults to 2 seconds. Minimum is 1 second and maximum is 5 minutes. Use an ISO-8601 duration, for example PT2S.

Agent result

Final answer from the agent, as text. Ask for JSON in the prompt and parse it with fromJson.

Run ID

Identifier of the Browser Use run

Run status

Terminal status reported by Browser Use. A successful task returns completed.

Total cost in USD

Total cost reported for the run

Input tokens

Input tokens reported for the run

Output tokens

Output tokens reported for the run

Unittoken

Input tokens reported by the Browser Use run

Unittoken

Output tokens reported by the Browser Use run

Unittoken

Input plus output tokens reported by the Browser Use run

More Plugins in this Category

Timefold
Timefold

Timefold plugin for Kestra

DataAI

2 tasks

1 blueprints

Pinecone
Pinecone

Interact with Pinecone, a managed vector database, from your Kestra workflows. Create serverless indexes, upsert vectors, query by similarity, fetch or delete vectors by ID, and inspect index statistics.

AIData

7 tasks

7 blueprints