> ## Documentation Index > Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt > Use this file to discover all available pages before exploring further. # GPT Image 2 > [Core Function] GPT Image 2 is a state-of-the-art text-to-image generation model. [Strengths] It excels at generating highly detailed, photorealistic images from text descriptions, with native support for ultra-high resolutions including 2K and 4K (up to 3840x2160). [Best For] Highly recommended for: cinematic landscapes, detailed character portraits, high-end commercial concept art, and any scenario requiring maximum resolution and visual fidelity. [Limitations] Do NOT use this model if you need a transparent background (e.g., for icons or UI assets), as it does not support the `background: transparent` parameter. [Routing] Use this model by default for all high-quality image generation requests. If the user explicitly asks for an image with a transparent background, route to GPT Image 1.5 instead. ## OpenAPI ````yaml /model-api/openai/openai-t2i.json post /openai/gpt-image-2 openapi: 3.1.0 info: description: The text-to-image models API from OpenAI. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai title: OpenAI Text-to-Image Models API servers: - url: https://api.modellix.ai/api/v1 description: The text-to-image models API from OpenAI. security: - bearerAuth: [] paths: /openai/gpt-image-2: post: tags: - GPT Image summary: GPT Image 2 description: >- [Core Function] GPT Image 2 is a state-of-the-art text-to-image generation model. [Strengths] It excels at generating highly detailed, photorealistic images from text descriptions, with native support for ultra-high resolutions including 2K and 4K (up to 3840x2160). [Best For] Highly recommended for: cinematic landscapes, detailed character portraits, high-end commercial concept art, and any scenario requiring maximum resolution and visual fidelity. [Limitations] Do NOT use this model if you need a transparent background (e.g., for icons or UI assets), as it does not support the `background: transparent` parameter. [Routing] Use this model by default for all high-quality image generation requests. If the user explicitly asks for an image with a transparent background, route to GPT Image 1.5 instead. operationId: gptImage2Async requestBody: description: Request payload for GPT Image 2 generation model. required: true content: application/json: schema: $ref: '#/components/schemas/GPTImage2Request' examples: basic: summary: Basic image generation value: prompt: >- A children's book drawing of a veterinarian using a stethoscope to listen to the heartbeat of a baby otter advanced_4k: summary: 4K high-resolution generation value: prompt: >- Cinematic landscape of a misty mountain range at golden hour, ultra detailed, photorealistic size: 3840x2160 quality: high responses: '200': description: Task submitted successfully content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: GPTImage2Request: description: Request payload for GPT Image 2 generation model. type: object required: - prompt properties: prompt: type: string description: Image description text, supports up to 32,000 characters minLength: 1 maxLength: 32000 example: >- A children's book drawing of a veterinarian using a stethoscope to listen to the heartbeat of a baby otter size: type: string description: >- Output size as width x height, or 'auto' for model-selected size. Presets are valid under OpenAI constraints (total pixels 655360-8294400, edges multiples of 16). Mapping: 1:1 1K/2K; 3:2 1K/2K; 2:3 1K/2K; 4:3 1K/2K; 3:4 1K/2K; 16:9 2K/4K; 9:16 2K/4K. No 1K for 16:9/9:16; no 4K for non-widescreen ratios. default: 1024x1024 enum: - auto - 1024x1024 - 2048x2048 - 1536x1024 - 3072x2048 - 1024x1536 - 2048x3072 - 1024x768 - 2048x1536 - 768x1024 - 1536x2048 - 2048x1152 - 3840x2160 - 1152x2048 - 2160x3840 example: 1024x1024 quality: type: string description: >- Image quality level. 'low': fast draft (default), 'medium': balanced, 'high': best quality default: low enum: - low - medium - high example: high AsyncTaskResponse: description: Response object for asynchronous task submission. type: object required: - code - message - data properties: code: type: integer description: Response code, 0 indicates success example: 0 message: type: string description: Response message example: success data: description: Detailed data about the submitted asynchronous task. type: object required: - status - task_id - model_id properties: status: type: string enum: - pending - processing description: Task status example: pending task_id: type: string description: Unique task identifier example: task-openai-abc123 model_id: type: string description: Model ID example: gpt-image-2 get_result: type: object description: API information to query the task result properties: method: type: string description: HTTP method example: GET url: type: string description: Full URL to query the task result example: https://api.modellix.ai/api/v1/tasks/task-openai-abc123 ErrorResponse: description: Standard error response object. type: object required: - code - message properties: code: type: integer description: Error code (equals HTTP status code) example: 400 message: type: string description: 'Error message in format ''Category: detail''' example: 'Invalid parameters: parameter ''prompt'' is required' responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: missing_prompt: summary: Missing required parameter value: code: 400 message: 'Invalid parameters: parameter ''prompt'' is required' invalid_size: summary: Invalid size parameter value: code: 400 message: 'Invalid parameters: size must be one of the supported values' content_violation: summary: Content policy violation value: code: 400 message: 'Content policy violation: prompt contains prohibited content' Unauthorized: description: Unauthorized - Invalid or missing API Key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 401 message: 'Authentication failed: invalid API key' TooManyRequests: description: Too many requests - Rate limit exceeded or insufficient quota headers: Retry-After: description: Seconds to wait before retrying (optional) schema: type: integer example: 20 X-RateLimit-Limit-Requests: description: Maximum requests per minute schema: type: integer example: 5 X-RateLimit-Limit-Tokens: description: Maximum tokens per minute schema: type: integer example: 100000 X-RateLimit-Remaining-Requests: description: Remaining requests in current window schema: type: integer example: 0 X-RateLimit-Remaining-Tokens: description: Remaining tokens in current window schema: type: integer example: 0 X-RateLimit-Reset-Requests: description: Time when request limit resets (RFC3339 format) schema: type: string example: '2024-04-23T12:00:00Z' X-RateLimit-Reset-Tokens: description: Time when token limit resets (RFC3339 format) schema: type: string example: '2024-04-23T12:00:00Z' content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: rate_limit: summary: Rate limit exceeded value: code: 429 message: 'Rate limit exceeded: too many requests, retry after 20 seconds' insufficient_quota: summary: Insufficient quota value: code: 429 message: >- Quota exceeded: insufficient quota, please check your plan and billing InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: server_error: summary: Server error value: code: 500 message: 'Internal server error: please try again later' service_unavailable: summary: Service unavailable value: code: 503 message: 'Service unavailable: OpenAI service is temporarily unavailable' securitySchemes: bearerAuth: type: http scheme: bearer description: 'API Key authentication. Format: `Bearer YOUR_API_KEY`.' ````