> ## 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. # Get Schema > Returns the request and response schema for a Media Model. Pass the model slug in the path (for example alibaba/qwen-image-3.0-pro). This endpoint is public and does not require an API key. The response includes servers (inference base URL) and post (OpenAPI-style operation: description, requestBody JSON Schema, examples, and async task responses). Use servers[0].url as the async generate URL; that call still requires a Bearer API key on https://api.modellix.ai. Resolve slugs from List Active Models. ## OpenAPI ````yaml /media-model-api/get-schema.json get /models/{model_slug}/api_schema openapi: 3.1.0 info: title: Media Model Schema API description: >- Public endpoint that returns the OpenAPI-style POST operation and inference server URL for a Media Model. No API key is required. version: 1.0.0 contact: name: Modellix API Support email: support@modellix.ai servers: - url: https://www.modellix.ai/ description: Modellix website (public, no authentication) security: [] paths: /models/{model_slug}/api_schema: get: summary: Get Schema description: >- Returns the request and response schema for a Media Model. Pass the model slug in the path (for example alibaba/qwen-image-3.0-pro). This endpoint is public and does not require an API key. The response includes servers (inference base URL) and post (OpenAPI-style operation: description, requestBody JSON Schema, examples, and async task responses). Use servers[0].url as the async generate URL; that call still requires a Bearer API key on https://api.modellix.ai. Resolve slugs from List Active Models. operationId: getMediaModelSchema parameters: - name: model_slug in: path required: true description: >- Model slug in `provider/model` form (for example `alibaba/qwen-image-3.0-pro`). Interpolate the slash as a literal path separator. Do not encode it as `%2F`. schema: type: string example: alibaba/qwen-image-3.0-pro pattern: ^[^/]+/[^/]+$ responses: '200': description: Media Model OpenAPI-style schema content: application/json: schema: $ref: '#/components/schemas/MediaModelApiSchema' examples: qwen_image_3_0_pro: summary: alibaba/qwen-image-3.0-pro value: servers: - url: >- https://api.modellix.ai/api/v1/alibaba/qwen-image-3.0-pro post: description: >- [Core Function] Qwen Image 3.0 Pro is Alibaba's latest text-to-image model with strong prompt following and photorealism. [Strengths] It supports free-form output size (width*height), optional negative prompts, intelligent prompt rewrite, batch generation of 1-6 images, and long structured prompts for complex layouts. [Best For] Highly recommended for: photorealistic stills, marketing posters with readable text, detailed scene compositions, multi-panel layouts, product hero shots, and multi-variant creative exploration (n up to 6). [Limitations] Do NOT use this if the user needs native 4K output, thinking-mode reasoning, or image editing with reference images (use Qwen Image 3.0 Pro Edit for edits). Keep total pixels within 512*512 to 2048*2048. Very long prompts combined with a long negative_prompt may exceed the model input capacity (about 4.5k tokens total). [Routing] Prefer this over Qwen Image 2.0 Pro for new Qwen Image text-to-image work. If the user provides reference image(s) to edit, route to Qwen Image 3.0 Pro Edit instead. operationId: qwenImage30ProAsync requestBody: content: application/json: examples: basic: summary: Basic image generation value: prompt: >- A cinematic still of an astronaut exploring an alien planet custom_size: summary: Custom size and batch value: 'n': 2 negative_prompt: blurry text, misspelling prompt: >- A movie poster with the title STELLAR ODYSSEY prompt_extend: true size: 1024*1536 schema: properties: 'n': default: 1 description: Number of images to generate (1-6) example: 1 maximum: 6 minimum: 1 type: integer negative_prompt: description: Negative prompt describing unwanted content example: blurry, low quality maxLength: 500 type: string prompt: description: >- Image description text, supports Chinese and English example: >- A serene Japanese garden with cherry blossoms maxLength: 4500 minLength: 1 type: string prompt_extend: default: true description: >- Whether to enable intelligent prompt rewriting. Default true (recommended). When enabled, the model rewrites the positive prompt using the mode specified by prompt_extend_mode; most effective for short or simple prompts. example: true type: boolean prompt_extend_mode: default: direct description: >- Prompt rewrite mode when prompt_extend is true. Default direct. direct: Direct Prompt Enhancement (DPE), suitable for most scenarios (T2I and I2I). agent: Agent Prompt Enhancement (APE), finer rewrite; text-to-image (T2I) only. enum: - direct - agent example: direct type: string seed: description: Random seed for reproducible results example: 42 maximum: 2147483647 minimum: 0 type: integer size: description: >- Output image resolution as width*height (e.g. 1024*1024). Optional; when omitted the model auto-selects. Total pixels should stay within 512*512 to 2048*2048. example: 1024*1024 pattern: ^\d+\*\d+$ type: string required: - prompt type: object required: true responses: '200': content: application/json: schema: properties: code: description: Response code, 0 indicates success example: 0 type: integer data: description: >- Detailed data about the submitted asynchronous task. properties: get_result: description: API information to query the task result properties: method: description: HTTP method example: GET type: string url: description: Full URL to query the task result example: >- https://api.modellix.ai/api/v1/tasks/task-abc123 type: string type: object model_id: description: Model ID example: model-123 type: string status: description: Task status enum: - pending - processing example: pending type: string task_id: description: Unique task identifier example: task-abc123 type: string required: - status - task_id - model_id type: object message: description: Response message example: success type: string required: - code - message - data type: object description: Task submitted successfully '400': content: application/json: example: code: 400 message: >- Invalid parameters: parameter 'prompt' is required schema: properties: code: description: Error code (equals HTTP status code) example: 400 type: integer message: description: 'Error message in format ''Category: detail''' example: >- Invalid parameters: parameter 'prompt' is required type: string required: - code - message type: object description: Invalid request parameters '401': content: application/json: example: code: 401 message: 'Authentication failed: invalid API key' schema: properties: code: description: Error code (equals HTTP status code) example: 400 type: integer message: description: 'Error message in format ''Category: detail''' example: >- Invalid parameters: parameter 'prompt' is required type: string required: - code - message type: object description: Unauthorized - Invalid or missing API Key '429': content: application/json: example: code: 429 message: >- Rate limit exceeded: 100 requests per minute, retry after 60 seconds schema: properties: code: description: Error code (equals HTTP status code) example: 400 type: integer message: description: 'Error message in format ''Category: detail''' example: >- Invalid parameters: parameter 'prompt' is required type: string required: - code - message type: object description: Too many requests - Rate limit exceeded headers: X-RateLimit-Limit: description: Maximum requests per minute schema: example: 100 type: integer X-RateLimit-Remaining: description: Remaining quota in current window schema: example: 0 type: integer X-RateLimit-Reset: description: Rate limit window reset time (Unix timestamp) schema: example: 1704067260 type: integer '500': content: application/json: example: code: 500 message: Internal server error schema: properties: code: description: Error code (equals HTTP status code) example: 400 type: integer message: description: 'Error message in format ''Category: detail''' example: >- Invalid parameters: parameter 'prompt' is required type: string required: - code - message type: object description: Internal server error summary: Qwen Image 3.0 Pro tags: - Qwen Image x-mint: href: alibaba/qwen-image-3-0-pro '404': description: Unknown model slug content: application/json: schema: $ref: '#/components/schemas/ModelNotFoundError' example: error: true url: http://www.modellix.ai/models/not-a-real/model-slug/api_schema statusCode: 404 statusMessage: Model Not Found message: Model Not Found components: schemas: MediaModelApiSchema: type: object required: - servers - post description: >- OpenAPI-style fragment for the model's async POST generate endpoint. Field shapes under post.requestBody and post.responses vary by model. properties: servers: type: array description: >- Inference server entries. POST the request body to servers[0].url (typically https://api.modellix.ai/api/v1/{model_slug}). That generate call requires a Bearer API key. minItems: 1 items: $ref: '#/components/schemas/MediaModelServer' post: $ref: '#/components/schemas/MediaModelPostOperation' ModelNotFoundError: type: object required: - error - statusCode - message description: >- Website-style error when the slug does not match a published Media Model. This is not the {code, message} envelope used on api.modellix.ai. properties: error: type: boolean example: true url: type: string description: Requested URL as recorded by the site example: http://www.modellix.ai/models/not-a-real/model-slug/api_schema statusCode: type: integer example: 404 statusMessage: type: string example: Model Not Found message: type: string example: Model Not Found MediaModelServer: type: object required: - url properties: url: type: string format: uri description: Base URL for the model's async generate POST example: https://api.modellix.ai/api/v1/alibaba/qwen-image-3.0-pro MediaModelPostOperation: type: object required: - description - operationId - requestBody - responses - summary description: >- OpenAPI-style POST operation for the model. requestBody and responses follow the same shapes as the corresponding Media Model docs page. properties: description: type: string description: >- Agent-oriented model description (Core Function, Strengths, Best For, Limitations, Routing) operationId: type: string description: Operation identifier for the async generate call example: qwenImage30ProAsync summary: type: string description: Short model title example: Qwen Image 3.0 Pro tags: type: array description: Optional series or family labels items: type: string requestBody: type: object description: >- JSON request body contract under content.application/json (schema, examples). Shape is model-specific. additionalProperties: true responses: type: object description: >- Async task submit responses (200, 400, 401, 429, 500). Shape is model-specific. additionalProperties: true x-mint: type: object description: >- Docs page metadata. href is the Media Models reference path without a leading slash. properties: href: type: string example: alibaba/qwen-image-3-0-pro ````