> ## Documentation Index > Fetch the complete documentation index at: https://docs.gbox.ai/llms.txt > Use this file to discover all available pages before exploring further. # Generate Coordinates Generate precise UI element coordinates using the **gbox-handy-1** model. This specialized model analyzes screenshots and instructions to identify exact coordinates for UI operations. ## Supported Actions The model supports three core actions that cover nearly all coordinate-based UI interactions: * **Click**: Identify precise tap/click coordinates for buttons, links, and interactive elements * **Drag**: Calculate start and end coordinates for drag operations (e.g., swipe, scroll bars) * **Scroll**: Determine optimal scroll coordinates and directions ## OpenAPI ````yaml post /model openapi: 3.0.0 info: title: GBOX Open API description: GBOX Open API Documentation version: '1.0' contact: {} servers: - url: https://gbox.ai/api/v1 description: Production Server security: [] tags: [] paths: /model: post: tags: - Model summary: Generate coordinates for a model operationId: ModelController_call parameters: [] requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ModelRequest' responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/ModelResponseData' security: - bearer: [] x-codeSamples: - lang: JavaScript source: "import GboxSDK from \"gbox-sdk\";\n\nconst gboxSDK = new GboxSDK({\n apiKey: process.env[\"GBOX_API_KEY\"] // This is the default and can be omitted\n});\n\nasync function main() {\n const result = await gboxSDK.model.call({\n\t\tmodel: \"gbox-handy-1\",\n screenshot: \"https://gru-activate2-public-assets.s3.us-west-2.amazonaws.com/jessica/screenshot-1759332945616-pu0ovj.png\",\n action: {\n type: \"click\",\n target: \"the VSCode app icon on the bottom dock\"\n }\n });\n\n console.log(\"Result:\");\n console.info(JSON.stringify(result, null, 2));\n}\n\nmain();" - lang: Python source: '# Coming soon' - lang: Go source: // Coming soon components: schemas: ModelRequest: type: object properties: model: type: string description: Model to use enum: - gbox-handy-1 example: gbox-handy-1 default: gbox-handy-1 screenshot: type: string description: >- Screenshot image as HTTP(S) URL or base64-encoded data URI. Supports both formats: 1) HTTP(S) URL pointing to an image file; 2) Base64-encoded data URI with format 'data:image/png;base64,[data]' or 'data:image/jpeg;base64,[data]'. Only PNG and JPEG formats are supported for base64. action: description: Structured action object (click or drag) oneOf: - $ref: '#/components/schemas/ClickAction' - $ref: '#/components/schemas/DragAction' - $ref: '#/components/schemas/ScrollAction' title: Model Request description: Model request required: - screenshot - action ModelResponseData: type: object properties: response: description: Model response data oneOf: - $ref: '#/components/schemas/ModelClickResponseData' - $ref: '#/components/schemas/ModelDragResponseData' - $ref: '#/components/schemas/ModelScrollResponseData' id: type: string description: >- Unique ID of this request, can be used for issue reporting and feedback example: 123e4567-e89b-12d3-a456-426614174000 title: Model Response Data description: Model response data structure required: - response - id ClickAction: type: object properties: type: type: string description: Action type enum: - click - drag - scroll example: click target: type: string description: Natural language description of what to click example: the VSCode app icon on the bottom dock maxLength: 2000 minLength: 1 title: Click Action description: Click action structure required: - type - target DragAction: type: object properties: type: type: string description: Action type enum: - click - drag - scroll example: drag target: type: string description: Natural language description of starting position example: the VSCode app icon maxLength: 2000 minLength: 1 destination: type: string description: Natural language description of ending position example: the desktop maxLength: 2000 minLength: 1 title: Drag Action description: Drag action structure required: - type - target - destination ScrollAction: type: object properties: type: type: string description: Action type enum: - click - drag - scroll example: scroll location: type: string description: >- Natural language description of the location where the scroll should originate. example: Side bar maxLength: 2000 minLength: 1 direction: type: string description: Scroll direction enum: - up - down - left - right example: up title: Scroll Action description: Scroll action structure required: - type - location - direction ModelClickResponseData: type: object properties: type: type: string description: Action type enum: - click - drag - scroll example: click coordinates: description: Click result data allOf: - $ref: '#/components/schemas/ClickResult' title: Model Click Response Data description: Model click response data structure required: - type - coordinates ModelDragResponseData: type: object properties: type: type: string description: Action type enum: - click - drag - scroll example: drag coordinates: description: Drag result data allOf: - $ref: '#/components/schemas/DragResult' title: Model Drag Response Data description: Drag response data structure required: - type - coordinates ModelScrollResponseData: type: object properties: type: type: string description: Action type enum: - click - drag - scroll example: scroll coordinates: description: Scroll result data allOf: - $ref: '#/components/schemas/ScrollResult' title: Model Scroll Response Data description: Scroll response data structure required: - type - coordinates ClickResult: type: object properties: x: type: number description: X coordinate. Returns -1 if no valid target is found. example: 520 'y': type: number description: Y coordinate. Returns -1 if no valid target is found. example: 340 title: Click Result description: Single click result with coordinates required: - x - 'y' DragResult: type: object properties: target: description: Starting coordinates allOf: - $ref: '#/components/schemas/Coordinates' destination: description: Ending coordinates allOf: - $ref: '#/components/schemas/Coordinates' title: Drag Result description: Single drag result with target and destination coordinates required: - target - destination ScrollResult: type: object properties: x: type: number description: X coordinate example: 520 'y': type: number description: Y coordinate example: 340 scrollX: type: number description: Horizontal scroll amount example: 100 scrollY: type: number description: Vertical scroll amount example: 100 title: Scroll Result description: Single scroll result with location and direction required: - x - 'y' - scrollX - scrollY Coordinates: type: object properties: x: type: number description: X coordinate. Returns -1 if no valid target is found. example: 520 'y': type: number description: Y coordinate. Returns -1 if no valid target is found. example: 340 title: Coordinates description: X and Y coordinates. Returns -1, -1 if no valid target is found. required: - x - 'y' securitySchemes: bearer: scheme: bearer bearerFormat: JWT type: http description: >- Enter your API Key in the format: Bearer . Get it from https://gbox.ai ````