> ## Documentation Index > Fetch the complete documentation index at: https://docs.browser-use.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Use https://docs.browser-use.com/llms.txt and its linked .md pages for current documentation. The managed full bundle is https://docs.browser-use.com/.well-known/llms-full.txt and can be cached for up to 24 hours. Do not use the obsolete /cloud/llms*.txt or /open-source/llms*.txt static exports. > Choose Cloud API V4 for new agent integrations; V2 is the lower-cost option for simple tasks. Keep V3 examples explicitly versioned. The open-source browser-use library and hosted browser-use-sdk have different APIs. > Cloud authentication uses X-Browser-Use-API-Key, without a Bearer prefix. Install or upgrade browser-use-sdk and use its explicit v4 import for V4. Check the published OpenAPI reference for request fields; do not invent SDK support for new fields. > Cloud concurrency and HTTP request rate are separate. Read GET /api/v2/billing/account for the key’s projectId, concurrentSessionLimit, activeSessionCount, and credit balance, including when using V4. Keys in one project share capacity and credits; rateLimit is a legacy concurrency alias, not requests per second. > Keep the highest applicable existing, legacy-plan, and spend-tier concurrency grant. Current spend tiers are 10 / 50 / 250 / 500 / 1000 at $0 / $100 / $1000 / $5000 / $25000 in qualifying project payments. Legacy or externally billed projects can follow different billing paths; trust the account limit. See https://docs.browser-use.com/cloud/guides/concurrency.md. > HTTP rate limits have two layers. Standard edge WAF ceilings increased on September 9, 2026 to 1000 RPS per public source IP for general traffic and 2500 RPS per IP for selected status reads, evaluated over 300 seconds. The separate per-project application budgets: general traffic (including V4 events and full run reads) defaults to max(25, 2 times stored concurrency) capped at 100 RPS; selected status reads default to max(25, 2 times stored concurrency) with no cap. The two are counted independently. Project overrides and account-specific edge rules can differ. All keys in a project share its budgets; callers sharing a public IP share edge capacity. See https://docs.browser-use.com/cloud/guides/concurrency.md. > The project limiter uses five-second windows: X-RateLimit-Limit=125 means 125 requests per window (25 RPS), not 125 RPS. Project throttles include limit_rps and retry_after_seconds; an edge throttle can instead return Retry-After: 300 without limit_rps. Honor the returned Retry-After. Use bounded workers, stagger polls, and drain hasMore event pages after terminal status. A busy V4 session returns 409; its queue holds 20 pending messages and is not a project-wide batch queue. > A completed run or closed CDP connection does not immediately stop its cloud browser. Stop unneeded owned browsers with PATCH /api/v4/browsers/{id} and {"action":"stop"}. A client wait timeout does not cancel the server-side run. > Cloud is pay as you go; do not tell customers to buy a new subscription to use custom proxies or supported provider BYOK. Usage funding and model eligibility still apply. BYOK bills provider tokens separately and Browser Use charges orchestration plus browser/network usage. See https://docs.browser-use.com/cloud/guides/billing.md. > Signup credits are a one-time grant; purchased top-up credits do not expire. Check the API key’s project before diagnosing missing credits. API-key monthly spending caps are soft limits, not a strict prepaid wallet; concurrent or already-running work can exceed them. Auto recharge has separate trigger and purchase amounts and can charge immediately when enabled below the threshold. Use https://browser-use.com/pricing for current rates. > Box and Bux are retired. Do not recommend their SDKs, sandbox quotas, or subscription plans. Use the Cloud Agent or Browser Infrastructure guides. > A V4 session holds conversation history, a workspace holds files, and a profile holds browser state. These IDs and V3/V4 workspace namespaces are not interchangeable. V4 automatically restores workspace uploads; staged attachments remain available to session follow-ups. Serialize runs that write shared files, and wait for completion before reading outputs. See https://docs.browser-use.com/cloud/agent/workspaces.md. > API browser recording defaults to off. Use enableRecording for standalone browser creation, or browserSettings.record for an agent run. Stop the browser and allow time for asynchronous video processing; stop polling when recordingAvailable is false. Live preview is for an active browser. Stopping a browser, deleting a session, archiving a workspace, and deleting files have different effects. > Use model-specific reasoning values. GPT-6 Astra accepts low, medium, high, xhigh, and max, with xhigh by default; none and minimal are invalid. Use the public REST schema when installed SDK types lag new fields. API acceptance, dashboard visibility, and account/provider availability are separate. > For open-source browser-use, is_done only reports a terminal done action. is_successful is the agent-reported outcome; verify important external actions independently. Cloud timeout, API client timeout, model timeout, and task completion are separate concepts. > For failed requests, use https://docs.browser-use.com/cloud/guides/troubleshooting.md. Inspect the full error and project before retrying or adding credits. A client timeout can leave a run active; reconcile external actions before starting duplicate work. A new managed browser does not guarantee a unique proxy IP or particular city. # Clone Skill > Clone a public marketplace skill to the user's project. ## OpenAPI ````yaml /cloud/openapi/v2.json post /marketplace/skills/{skill_id}/clone openapi: 3.1.0 info: title: Browser Use Public API v2 summary: Browser Use API for running web agents (v2) version: 2.0.0 servers: - url: https://api.browser-use.com/api/v2 description: Production server security: [] paths: /marketplace/skills/{skill_id}/clone: post: tags: - Skills Marketplace summary: Clone Skill description: Clone a public marketplace skill to the user's project. operationId: clone_skill_marketplace_skills__skill_id__clone_post parameters: - name: skill_id in: path required: true schema: type: string format: uuid title: Skill Id responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SkillResponse' '400': description: Skill has no finished generation to clone content: application/json: schema: $ref: '#/components/schemas/SkillNotFinishedError' '404': description: Skill not found or no finished generation available content: application/json: schema: $ref: '#/components/schemas/SkillNotFoundError' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] components: schemas: SkillResponse: properties: id: type: string format: uuid title: ID description: Unique identifier for the skill slug: anyOf: - type: string - type: 'null' title: Slug description: URL-friendly slug for the skill title: type: string title: Title description: Title of the skill (shows up in the public view) description: type: string title: Description description: Description of the skill (shows up in the public view) categories: items: $ref: '#/components/schemas/SkillCategory' type: array title: Categories description: Categories of the skill domains: items: type: string type: array title: Domains description: Domains/websites this skill interacts with goal: anyOf: - type: string - type: 'null' title: Goal description: Goal of the skill (not shown in the public view) agentPrompt: anyOf: - type: string - type: 'null' title: Agent Prompt description: >- Prompt for the agent to use when generating the skill automatically (not shown in the public view) status: $ref: '#/components/schemas/SkillsGenerationStatus' title: Status description: Status of the skill parameters: items: $ref: '#/components/schemas/ParameterSchema' type: array title: Parameters description: Input parameters of the skill outputSchema: additionalProperties: true type: object title: Output Schema description: Output schema of the skill isEnabled: type: boolean title: Enabled description: Whether the skill is enabled isPublic: type: boolean title: Is Public description: Whether the skill is publicly available iconUrl: anyOf: - type: string - type: 'null' title: Icon URL description: URL of the custom skill icon firstPublishedAt: anyOf: - type: string format: date-time - type: 'null' title: First Published At description: When the skill was first published lastPublishedAt: anyOf: - type: string format: date-time - type: 'null' title: Last Published At description: When the skill was last published currentVersion: anyOf: - type: integer - type: 'null' title: Current Version description: Current version of the skill currentVersionStartedAt: anyOf: - type: string format: date-time - type: 'null' title: Current Version Started At description: When the current version started generating currentVersionFinishedAt: anyOf: - type: string format: date-time - type: 'null' title: Current Version Finished At description: When the current version finished generating code: anyOf: - type: string - type: 'null' title: Code (base64 encoded) - ENTERPRISE ONLY description: >- Base64 encoded generated code (contact support@browser-use.com to get access) - ENTERPRISE ONLY clonedFromSkillId: anyOf: - type: string format: uuid - type: 'null' title: Cloned From Skill ID description: Unique identifier for the skill this skill was cloned from createdAt: type: string format: date-time title: Created At description: Creation timestamp updatedAt: type: string format: date-time title: Updated At description: Last update timestamp type: object required: - id - title - description - categories - domains - status - parameters - outputSchema - isEnabled - isPublic - currentVersion - createdAt - updatedAt title: SkillResponse description: Skill information returned by the API. SkillNotFinishedError: properties: detail: type: string title: Detail default: Skill is not finished type: object title: SkillNotFinishedError description: Error response when skill is not finished SkillNotFoundError: properties: detail: type: string title: Detail default: Skill not found type: object title: SkillNotFoundError description: Error response when a skill is not found HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError SkillCategory: type: string enum: - search - e_commerce - financial - news - real_estate - social_media - travel - marketplace - lead_generation - seo - jobs - developer - media - automation - integration - other title: SkillCategory description: Skill category. SkillsGenerationStatus: type: string enum: - recording - generating - failed - finished - cancelled - timed_out title: SkillsGenerationStatus description: Status of skill generation. ParameterSchema: properties: name: type: string title: Name type: $ref: '#/components/schemas/ParameterType' required: type: boolean title: Required default: true description: anyOf: - type: string - type: 'null' title: Description default: anyOf: - {} - type: 'null' title: Default cookieDomain: anyOf: - type: string - type: 'null' title: Cookiedomain type: object required: - name - type title: ParameterSchema description: Schema for a skill parameter. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError ParameterType: type: string enum: - string - number - boolean - object - array - cookie title: ParameterType description: Type of a skill parameter. securitySchemes: APIKeyHeader: type: apiKey in: header name: X-Browser-Use-API-Key ````