> ## Documentation Index > Fetch the complete documentation index at: https://aisa.one/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > - Base URLs: models `https://api.aisa.one/v1` (Gemini GenerateContent: `https://api.aisa.one/v1beta`); data APIs `https://api.aisa.one/apis/v1`. The `servers` of each operation in https://aisa.one/openapi.yaml is authoritative. > - Auth: `Authorization: Bearer $AISA_API_KEY`. Never print, log, or commit the key. > - MCP (preferred for agents): `https://mcp.aisa.one/mcp`, signed in with OAuth, so there is no key to paste. > - Agent Skill: `npx skills add AIsa-team/agent-skills --skill aisa`. Fallback with the AIsa CLI: `aisa skills install aisa`. > - Spending: docs, https://aisa.one/models, https://aisa.one/api, `/v1/models`, and MCP `search`, `list_categories`, `get_details`, `batch_quote`, and the `account` operation are free. Quote the exact calls before running them (MCP `batch_quote`, CLI `aisa quote --json`). If the quote reports `auto_execute_eligible: true`, run it unless the user set a tighter limit or asked only for a quote. Otherwise, tell the user in one message the planned calls, the quoted price, and a total USD budget for the task, then wait for approval. Direct HTTP calls follow the stricter rule at https://aisa.one/docs/get-started/cli.md#direct-http-fallback. Do not make paid calls to test availability. Full rule: https://aisa.one/llms.txt # Create a video generation task > Starts an asynchronous video generation task and returns it with status queued. The gateway requires model; the remaining fields are the selected model's own request fields and are forwarded to it. A video usually takes one to three minutes: poll retrieveVideoGeneration with the returned id until status is completed, failed or cancelled. Only a 503 whose code is video_submission_pending, with a non-empty id, means the task and its charge authorization were kept: retrieve it with that id and do not submit a replacement. Any other 503 means the service or the provider was unavailable and no task is pending; retry later. With X-AISA-Cost-Mode: quote the route returns a cost_estimate instead and creates no task. A request reference price is not currently available; use a request quote where supported. Account-specific pricing and final settlement may differ. ## Request contract * **Method and path:** POST /v1/video/generations * **Availability:** enabled * **Request URL template:** `https://api.aisa.one/v1/video/generations` * **X-AISA-Cost-Mode:** header; optional * **Runtime facts:** b05bd10c1f65804d1365e16e8d0787c01638f0abdea53ee0e7f966e42df0f0b5 [Complete OpenAPI definition](https://aisa.one/docs/openapi/media-generation.json) Effective request and pricing declaration (including authentication and referenced schemas): ```json theme={null} { "operationId": "createVideoGeneration", "method": "POST", "path": "/v1/video/generations", "servers": [ { "url": "https://api.aisa.one" } ], "parameters": [ { "description": "Return a free, read-only cost quote for this caller and payload instead of generating.", "in": "header", "name": "X-AISA-Cost-Mode", "schema": { "enum": [ "quote" ], "type": "string" } } ], "security": [ { "bearerAuth": [] } ], "requestBody": { "content": { "application/json": { "example": { "content": [ { "text": "A small red boat on a calm lake at dawn", "type": "text" } ], "duration": 5, "generate_audio": true, "model": "dreamina-seedance-2-0-260128", "ratio": "16:9", "watermark": false }, "schema": { "additionalProperties": true, "properties": { "content": { "description": "Prompt and reference media, for Seedance models.", "items": { "additionalProperties": true, "properties": { "image_url": { "properties": { "url": { "type": "string" } }, "type": "object" }, "role": { "description": "For images: first_frame, last_frame or reference_image; for videos: reference_video.", "type": "string" }, "text": { "type": "string" }, "type": { "description": "text, image_url or video_url.", "type": "string" }, "video_url": { "properties": { "url": { "type": "string" } }, "type": "object" } }, "required": [ "type" ], "type": "object" }, "type": "array" }, "duration": { "description": "Output length in seconds; part of the price.", "minimum": 1, "type": "integer" }, "generate_audio": { "type": "boolean" }, "model": { "description": "A video model from GET /v1/models, for example dreamina-seedance-2-0-260128 or wan2.7-t2v.", "minLength": 1, "type": "string" }, "prompt": { "description": "Text prompt, for models that take a plain prompt.", "type": "string" }, "ratio": { "description": "Aspect ratio, for example 16:9, 9:16 or 1:1.", "type": "string" }, "resolution": { "description": "For example 720p or 1080p; part of the price.", "type": "string" }, "watermark": { "type": "boolean" } }, "required": [ "model" ], "type": "object" } } }, "required": true }, "x-aisa-status": "enabled", "x-aisa-pricing": { "description": "Charged at the selected model's catalog price, which can depend on the requested resolution and duration and is listed per second, per request or by tokens. The charge is held at submission and settled when the task ends. A quote for the caller and payload says whether its amount is exact or an estimate.", "estimate_source": "unavailable", "estimate_unavailable_reason": "model_dependent_price", "kind": "model_catalog" }, "components": { "securitySchemes": { "bearerAuth": { "scheme": "bearer", "type": "http" } } } } ``` ## Cost and request rules A request reference price is not currently available; use a request quote where supported. Account-specific pricing and final settlement may differ. Published reference values are not an account-specific quote or a settled charge. For endpoints supporting X-AISA-Cost-Mode: quote, obtain a free quote for your exact request before execution; reconcile the settled cost with response metadata and Usage Logs. USD amounts use 1,000,000 integer micro-USD per dollar. ## OpenAPI ````yaml openapi/media-generation.json POST /v1/video/generations openapi: 3.1.0 info: description: >- Image and video generation on AIsa models. The model field selects the model; GET /v1/models lists the enabled image and video models and the routes each one serves. title: Media Generation version: '1' x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-catalogs: media-generation: description: >- Image and video generation on AIsa models. The model field selects the model; GET /v1/models lists the enabled image and video models and the routes each one serves. title: Media Generation x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-document: facts_hash: b05bd10c1f65804d1365e16e8d0787c01638f0abdea53ee0e7f966e42df0f0b5 generator_version: '3' protocol_version: '1' schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-configured-paths: - /v1/images/generations - /v1/video/generations - /v1/video/generations/{task_id} x-aisa-document: composer_version: '26' document_hash: sha256:db7f1b10e4feec69fd541e25bc0aa70851eb7596fab4af0d9d2b0dc9e0f10238 facts_hash: b05bd10c1f65804d1365e16e8d0787c01638f0abdea53ee0e7f966e42df0f0b5 generator_version: '3' protocol_version: '1' response_pending: [] schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-provider: media-generation servers: - url: https://api.aisa.one security: - bearerAuth: [] paths: /v1/video/generations: post: summary: Create a video generation task description: >- Starts an asynchronous video generation task and returns it with status queued. The gateway requires model; the remaining fields are the selected model's own request fields and are forwarded to it. A video usually takes one to three minutes: poll retrieveVideoGeneration with the returned id until status is completed, failed or cancelled. Only a 503 whose code is video_submission_pending, with a non-empty id, means the task and its charge authorization were kept: retrieve it with that id and do not submit a replacement. Any other 503 means the service or the provider was unavailable and no task is pending; retry later. With X-AISA-Cost-Mode: quote the route returns a cost_estimate instead and creates no task. A request reference price is not currently available; use a request quote where supported. Account-specific pricing and final settlement may differ. operationId: createVideoGeneration parameters: - description: >- Return a free, read-only cost quote for this caller and payload instead of generating. in: header name: X-AISA-Cost-Mode schema: enum: - quote type: string requestBody: content: application/json: example: content: - text: A small red boat on a calm lake at dawn type: text duration: 5 generate_audio: true model: dreamina-seedance-2-0-260128 ratio: '16:9' watermark: false schema: additionalProperties: true properties: content: description: Prompt and reference media, for Seedance models. items: additionalProperties: true properties: image_url: properties: url: type: string type: object role: description: >- For images: first_frame, last_frame or reference_image; for videos: reference_video. type: string text: type: string type: description: text, image_url or video_url. type: string video_url: properties: url: type: string type: object required: - type type: object type: array duration: description: Output length in seconds; part of the price. minimum: 1 type: integer generate_audio: type: boolean model: description: >- A video model from GET /v1/models, for example dreamina-seedance-2-0-260128 or wan2.7-t2v. minLength: 1 type: string prompt: description: Text prompt, for models that take a plain prompt. type: string ratio: description: Aspect ratio, for example 16:9, 9:16 or 1:1. type: string resolution: description: For example 720p or 1080p; part of the price. type: string watermark: type: boolean required: - model type: object required: true responses: '202': content: application/json: schema: additionalProperties: false properties: completed_at: description: Unix seconds; present once the task has ended. type: integer created_at: description: Unix seconds. type: integer error: properties: message: type: string type: object id: type: string model: type: string object: const: video.generation type: string progress: description: For example 0% or 100%. type: string result: description: >- The model's output once completed, including the video URL (video_url or url). status: enum: - queued - in_progress - completed - failed - cancelled - unknown type: string required: - id - object - status - model - created_at - progress type: object description: The task was created. '503': content: application/json: schema: anyOf: - additionalProperties: false properties: code: const: video_submission_pending type: string error: type: string id: description: The kept task; pass it to retrieveVideoGeneration. minLength: 1 type: string required: - error - code - id type: object - type: object description: >- Either the service or the provider was unavailable and no task is pending (retry later), or the submission needs reconciliation. Only the second has code video_submission_pending and a non-empty id: that task and its charge authorization are kept; retrieve it with the id and do not submit a replacement. default: description: >- Validation, authentication, balance or provider error. Provider refusals, such as content checks, keep their 4xx status. x-codeSamples: - label: Reference example lang: text source: >- # Fixed reference example. Playground inputs do not update this sample. curl --request POST \ --url https://api.aisa.one/v1/video/generations \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data '{ "model": "dreamina-seedance-2-0-260128", "content": [ { "type": "text", "text": "A small red boat on a calm lake at dawn" } ], "ratio": "16:9", "duration": 5, "generate_audio": true, "watermark": false }' components: securitySchemes: bearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.