> ## Documentation Index > Fetch the complete documentation index at: https://docs.omnimux.ai/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Public hosts only: console https://omnimux.ai/dashboard · API https://api.omnimux.ai · docs https://docs.omnimux.ai. > Gateway auth is Authorization: Bearer sk-… on https://api.omnimux.ai/v1 (OpenAI-compatible Chat Completions and related paths). > Discover pages from /llms.txt; full site dump /llms-full.txt; product skill /skill.md; docs search MCP /mcp. Prefer .md page URLs for Markdown. > Default docs locale is en; zh mirrors the same relative paths. Do not invent model ids not present on live pricing or the complete API pages. # MiniMax H3 Max > MiniMax H3 Max video API Use text\_to\_video without media, or first\_frame with exactly one image. video\_multi\_ref accepts at most 9 images, 3 videos and 3 audio files, 12 references total, with at least one image or video. Order within each collection is preserved. Use one field spelling per media kind. Replace legacy 720p with explicit 768P. Completed jobs without usable artifacts remain retryable; failure/cancellation takes precedence over stale artifacts. Status reads do not own billing settlement. Pricing follows the current catalog; no fixed generation latency is guaranteed. [Query Video Task](/en/api-reference/tasks/video-task) · [Pricing](/en/api-reference/account/pricing) ## OpenAPI ````yaml openapi/ops/video/minimax-h3-max.json POST /v1/video/generations openapi: 3.0.3 info: title: minimax-h3-max version: 1.0.0 servers: - url: https://api.omnimux.ai security: [] paths: /v1/video/generations: post: summary: MiniMax H3 video generation operationId: minimax_h3_max requestBody: required: true content: application/json: schema: type: object required: - model - prompt properties: model: type: string enum: - minimax/h3-max prompt: type: string minLength: 1 maxLength: 50000 operation: type: string enum: - text_to_video - first_frame - video_multi_ref description: >- Must agree with media: text uses none; first_frame requires one image only. image_url: type: string format: uri description: HTTP(S) first-frame image; do not combine with image_urls. image_urls: type: array items: type: string format: uri maxItems: 9 description: Ordered images; one field spelling per media kind. resolution: type: string enum: - 480P - 768P - 1080P default: 768P description: >- Case/whitespace normalized. 720p is rejected; select 768P explicitly. duration: oneOf: - type: integer enum: - 5 - 10 - type: string enum: - '5' - '10' default: 5 aspect_ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' prompt_optimizer: type: boolean default: true video_urls: type: array items: type: string format: uri maxItems: 3 description: Ordered references. Total <=12, at least one image or video. audio_urls: type: array items: type: string format: uri maxItems: 3 description: Ordered references. Total <=12, at least one image or video. image_with_roles: type: array minItems: 1 maxItems: 1 description: >- First-frame role form. Do not combine with image_url/image_urls; not accepted by video_multi_ref. items: type: object required: - url - role properties: url: type: string format: uri role: type: string enum: - first_frame example: model: minimax/h3-max operation: first_frame prompt: The camera moves around the subject image_url: https://example.com/first-frame.png resolution: 768P duration: 5 responses: '200': description: 'Queued video task: id, task_id, model, status=queued, created' content: application/json: schema: type: object properties: id: type: string task_id: type: string model: type: string object: type: string enum: - video status: type: string enum: - queued created: type: integer example: id: task_example task_id: task_example object: video model: minimax/h3-max status: queued created: 1788926400 '400': description: Invalid media, operation or resolution content: application/json: schema: oneOf: - $ref: '#/components/schemas/TaskError' - $ref: '#/components/schemas/GatewayError' description: >- Task validation errors use code/message/data; authentication or gateway middleware may use an error envelope. example: code: invalid_request message: 720p is retired for H3; explicitly select 768p data: null '401': description: Invalid API key content: application/json: schema: oneOf: - $ref: '#/components/schemas/TaskError' - $ref: '#/components/schemas/GatewayError' description: >- Task validation errors use code/message/data; authentication or gateway middleware may use an error envelope. '402': description: Insufficient quota content: application/json: schema: oneOf: - $ref: '#/components/schemas/TaskError' - $ref: '#/components/schemas/GatewayError' description: >- Task validation errors use code/message/data; authentication or gateway middleware may use an error envelope. '429': description: Rate limited content: application/json: schema: oneOf: - $ref: '#/components/schemas/TaskError' - $ref: '#/components/schemas/GatewayError' description: >- Task validation errors use code/message/data; authentication or gateway middleware may use an error envelope. '500': description: Gateway error content: application/json: schema: oneOf: - $ref: '#/components/schemas/TaskError' - $ref: '#/components/schemas/GatewayError' description: >- Task validation errors use code/message/data; authentication or gateway middleware may use an error envelope. security: - bearerAuth: [] components: schemas: TaskError: type: object required: - code - message properties: code: type: string message: type: string data: nullable: true description: Additional task error data, commonly null. GatewayError: type: object required: - error properties: error: type: object properties: message: type: string type: type: string code: nullable: true securitySchemes: bearerAuth: type: http scheme: bearer ````