> ## Documentation Index > Fetch the complete documentation index at: https://docs.platform.qubrid.com/llms.txt > Use this file to discover all available pages before exploring further. # Extract Text > Extract text from images using OCR-capable vision models. ## OpenAPI ````yaml /ocr/openapi.json POST /chat/completions openapi: 3.0.3 info: title: Qubrid OCR API version: 1.0.0 description: >- Extract and recognize text from images using OCR-specialized vision models through the OpenAI-compatible chat completions API. servers: - url: https://platform.qubrid.com/v1 security: - BearerAuth: [] paths: /chat/completions: post: tags: - OCR summary: Extract Text from Images with OCR description: >- Use specialized OCR vision models to extract and recognize text from images via the OpenAI-compatible chat completions API. operationId: createOCRCompletion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/OCRRequest' examples: Basic OCR: summary: Extract text from a document image value: model: Hunyuan/Hunyuan-OCR-1B messages: - role: user content: - type: text text: >- Extract all text from this image and preserve the layout structure. - type: image_url image_url: url: https://example.com/document.png max_tokens: 8192 temperature: 0.1 top_p: 1 stream: false OCR with Layout: summary: Extract text preserving document layout and structure value: model: Hunyuan/Hunyuan-OCR-1B messages: - role: user content: - type: text text: >- Extract all text from this document image while preserving the original layout, structure, and formatting. - type: image_url image_url: url: https://example.com/form.jpg max_tokens: 8192 temperature: 0.05 stream: false responses: '200': description: OCR text extraction completed successfully content: application/json: schema: $ref: '#/components/schemas/OCRResponse' example: id: chatcmpl-ocr-123456 object: chat.completion created: 1710000000 model: Hunyuan/Hunyuan-OCR-1B choices: - index: 0 message: role: assistant content: |- INVOICE #2024-001 Date: March 30, 2024 Billed To: John Smith 123 Main Street New York, NY 10001 Items: 1. Service A - $100.00 2. Service B - $250.00 Total: $350.00 finish_reason: stop '400': description: >- Bad request - missing required fields, invalid values, or malformed JSON content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized - missing or invalid API key content: application/json: schema: $ref: '#/components/schemas/AuthenticationErrorResponse' '402': description: Insufficient credits to process the request content: application/json: schema: $ref: '#/components/schemas/InsufficientQuotaErrorResponse' '403': description: >- Forbidden - authenticated but not allowed to access this model or resource content: application/json: schema: $ref: '#/components/schemas/PermissionErrorResponse' '404': description: >- Model not found - the specified OCR model does not exist or is not available content: application/json: schema: $ref: '#/components/schemas/ModelNotFoundErrorResponse' '413': description: Payload too large - input exceeds the model context window content: application/json: schema: $ref: '#/components/schemas/ContextLengthExceededErrorResponse' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/RateLimitErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' '502': description: >- Bad gateway - upstream OCR provider is unavailable or returned an error content: application/json: schema: $ref: '#/components/schemas/BackendUnavailableErrorResponse' '504': description: Gateway timeout - upstream OCR provider took too long to respond content: application/json: schema: $ref: '#/components/schemas/GatewayTimeoutErrorResponse' security: - BearerAuth: [] components: schemas: OCRRequest: type: object required: - model - messages properties: model: type: string example: Hunyuan/Hunyuan-OCR-1B description: The OCR-specialized vision model to use for text extraction. messages: type: array description: >- Chat-style input containing text instructions and image content for OCR processing. items: type: object properties: role: type: string example: user content: type: array items: type: object properties: type: type: string example: text text: type: string example: >- Extract all text from this image and preserve the layout structure. image_url: type: object properties: url: type: string example: https://example.com/document.png description: >- Publicly accessible image URL containing text to extract. max_tokens: type: integer default: 8192 description: Maximum number of tokens to generate in the OCR response. temperature: type: number default: 0.1 description: >- Sampling temperature for text extraction (lower = more deterministic). top_p: type: number default: 1 description: Nucleus sampling parameter for OCR output. stream: type: boolean default: false description: Whether to stream OCR output incrementally. OCRResponse: type: object description: Standard OpenAI-compatible chat completion response with extracted text. properties: id: type: string example: chatcmpl-ocr-123456 object: type: string example: chat.completion created: type: integer example: 1710000000 model: type: string example: Hunyuan/Hunyuan-OCR-1B choices: type: array items: type: object properties: index: type: integer example: 0 message: type: object properties: role: type: string example: assistant content: type: string example: |- Header: Important Document Section 1: Introduction This document contains important information... Section 2: Details Key points and data extracted from the image... finish_reason: type: string example: stop ErrorResponse: type: object required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: 'Missing required parameter: ''messages''.' type: type: string example: invalid_request_error description: Machine-readable error category. code: type: string example: invalid_request description: Specific machine-readable error code. param: type: string nullable: true example: messages description: The request field that caused the error, or null. request_id: type: string example: req-qubrid-abc123 description: Unique request identifier for debugging and support. AuthenticationErrorResponse: type: object description: Returned when authentication fails. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: Missing authentication credentials. type: type: string example: authentication_error code: type: string example: missing_api_key param: type: string nullable: true example: null request_id: type: string example: req-qubrid-abc123 InsufficientQuotaErrorResponse: type: object description: >- Returned when the account does not have enough credits to complete the request. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: >- Insufficient credits to process this request. Please recharge your account. type: type: string example: insufficient_quota code: type: string example: insufficient_quota param: type: string nullable: true example: null request_id: type: string example: req-qubrid-abc123 PermissionErrorResponse: type: object description: >- Returned when the authenticated account does not have permission to access the resource. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: >- Permission denied: You do not have permission to access this model. type: type: string example: permission_error code: type: string example: insufficient_quota param: type: string nullable: true example: null request_id: type: string example: req-qubrid-abc123 ModelNotFoundErrorResponse: type: object description: >- Returned when the specified OCR model does not exist or is not available. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: The model 'ocr-ultra' does not exist or is not available. type: type: string example: invalid_request_error code: type: string example: model_not_found param: type: string nullable: true example: model request_id: type: string example: req-qubrid-abc123 ContextLengthExceededErrorResponse: type: object description: Returned when the input exceeds the model's maximum context window. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: >- Context length exceeded: The input exceeds the model's maximum context length. type: type: string example: invalid_request_error code: type: string example: context_length_exceeded param: type: string nullable: true example: messages request_id: type: string example: req-qubrid-abc123 RateLimitErrorResponse: type: object description: Returned when request rate limits are exceeded. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: Rate limit exceeded. Please try again later. type: type: string example: rate_limit_error code: type: string example: rate_limit_exceeded param: type: string nullable: true example: null request_id: type: string example: req-qubrid-abc123 ServerErrorResponse: type: object description: Returned when an internal server error occurs. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: An unexpected error occurred while processing the request. type: type: string example: server_error code: type: string example: internal_error param: type: string nullable: true example: null request_id: type: string example: req-qubrid-abc123 BackendUnavailableErrorResponse: type: object description: >- Returned when the upstream OCR provider is temporarily unavailable or could not be reached. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: The backend service is temporarily unavailable. type: type: string example: server_error code: type: string example: backend_unavailable param: type: string nullable: true example: null request_id: type: string example: req-qubrid-abc123 GatewayTimeoutErrorResponse: type: object description: Returned when the upstream OCR provider took too long to respond. required: - error properties: error: type: object required: - message - type - code - request_id properties: message: type: string example: The request timed out while waiting for the backend service. type: type: string example: server_error code: type: string example: backend_error param: type: string nullable: true example: null request_id: type: string example: req-qubrid-abc123 securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key ````