> ## 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. # Update Session > Stop a session and all its running tasks. ## OpenAPI ````yaml /cloud/openapi/v2.json patch /sessions/{session_id} 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: /sessions/{session_id}: patch: tags: - Sessions summary: Update Session description: Stop a session and all its running tasks. operationId: update_session_sessions__session_id__patch parameters: - name: session_id in: path required: true schema: type: string format: uuid title: Session Id requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/UpdateSessionRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SessionView' '404': description: Session not found content: application/json: schema: $ref: '#/components/schemas/SessionNotFoundError' '422': description: Request validation failed content: application/json: schema: $ref: '#/components/schemas/ValidationError' security: - APIKeyHeader: [] components: schemas: UpdateSessionRequest: properties: action: $ref: '#/components/schemas/SessionUpdateAction' title: Action description: The action to perform on the session type: object required: - action title: UpdateSessionRequest description: Request model for updating session state. SessionView: properties: id: type: string format: uuid title: ID description: Unique identifier for the session status: $ref: '#/components/schemas/SessionStatus' title: Status description: Current status of the session (active/stopped) liveUrl: anyOf: - type: string - type: 'null' title: Live URL description: URL where the browser can be viewed live in real-time recordingUrl: anyOf: - type: string - type: 'null' title: Recording URL description: >- Presigned URL to download the session recording (available after session ends, if recording was enabled) startedAt: type: string format: date-time title: Started At description: Timestamp when the session was created and started finishedAt: anyOf: - type: string format: date-time - type: 'null' title: Finished At description: Timestamp when the session was stopped (None if still active) tasks: items: $ref: '#/components/schemas/TaskItemView' type: array title: Tasks description: List of tasks associated with this session publicShareUrl: anyOf: - type: string - type: 'null' title: Public Share URL description: Optional URL to access the public share of the session persistMemory: type: boolean title: Persist Memory description: >- Whether tasks in this session share memory and history with each other default: true keepAlive: type: boolean title: Keep Alive description: Whether the browser session stays alive after tasks complete default: true proxyUsedMb: type: string pattern: ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$ title: Proxy Used MB description: Amount of proxy data used in MB default: '0' proxyCost: type: string pattern: ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$ title: Proxy Cost description: Cost of proxy usage in USD default: '0' type: object required: - id - status - startedAt - tasks title: SessionView description: >- View model for representing a (browser) session with its associated tasks. SessionNotFoundError: properties: detail: type: string title: Detail default: Session not found type: object title: SessionNotFoundError description: Error response when a session is not found 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 SessionUpdateAction: type: string enum: - stop title: SessionUpdateAction description: |- Available actions that can be performed on a session Attributes: STOP: Stop the session and all its associated tasks (cannot be undone) SessionStatus: type: string enum: - active - stopped title: SessionStatus description: |- Enumeration of possible agent session states Attributes: ACTIVE: Agent session is currently active and running STOPPED: Agent session has been stopped and is no longer active TaskItemView: properties: id: type: string format: uuid title: ID description: Unique identifier for the task sessionId: type: string format: uuid title: Session ID description: ID of the session this task belongs to llm: type: string title: LLM description: The LLM model used for this task represented as a string task: type: string title: Task description: The task prompt/instruction given to the agent status: $ref: '#/components/schemas/TaskStatus' createdAt: type: string format: date-time title: Created At description: Naive UTC timestamp when the task was created startedAt: anyOf: - type: string format: date-time - type: 'null' title: Started At description: >- Naive UTC timestamp when the task was started (None if task has not started yet) finishedAt: anyOf: - type: string format: date-time - type: 'null' title: Finished At description: Naive UTC timestamp when the task completed (None if still running) metadata: additionalProperties: true type: object title: Metadata description: >- Optional additional metadata associated with the task set by the user default: {} output: anyOf: - type: string - type: 'null' title: Output description: Final output/result of the task browserUseVersion: anyOf: - type: string - type: 'null' title: Browser Use Version description: >- Version of browser-use used for this task (older tasks may not have this set) isSuccess: anyOf: - type: boolean - type: 'null' title: Is Success description: Whether the task was successful (self-reported by the agent) judgement: anyOf: - type: string - type: 'null' title: Judgement description: Stringified JSON object containing the full report from the judge judgeVerdict: anyOf: - type: boolean - type: 'null' title: Judge Verdict description: >- Judge verdict - True if the judge found the task to be successful, False otherwise (None if judge is not enabled) cost: anyOf: - type: string pattern: ^(?!^[-+.]*$)[+-]?0*\d*\.?\d*$ - type: 'null' title: Cost description: >- Total cost of the task in USD. This is the sum of all step costs incurred during task execution. suggestions: anyOf: - items: additionalProperties: true type: object type: array - type: 'null' title: Suggestions description: >- List of actionable suggestions for improving task configuration based on detected issues during execution. type: object required: - id - sessionId - llm - task - status - createdAt title: TaskItemView description: View model for representing a task with its execution details TaskStatus: type: string enum: - created - started - finished - failed - stopped title: TaskStatus description: |- Enumeration of possible task execution states Attributes: CREATED: Task has been created but not yet started. STARTED: Task has been started and is currently running. FINISHED: Task has finished and the agent has completed the task. FAILED: Task execution failed due to an error. STOPPED: Task execution has been manually stopped (cannot be resumed). securitySchemes: APIKeyHeader: type: apiKey in: header name: X-Browser-Use-API-Key ````