> ## 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

# Wan API - Access Alibaba Wan Video and Image Models via AIsa

> AIsa guide to Alibaba Wan model IDs, including wan3.0-video and Wan 2.7, with an API compatible with the official DashScope (Alibaba Cloud Model Studio) video generation API.

AIsa is an Alibaba Cloud Key Account Partner. Use one AIsa API key to access Alibaba Wan video and image models.

For Wan video, AIsa is compatible with the official DashScope (Alibaba Cloud Model Studio) API: the official DashScope SDK and existing DashScope code work after changing only the base URL and API key. Wan video is also available through the AIsa video API, `POST /v1/video/generations`. Wan image models use `POST /v1/images/generations` and `POST /v1/images/edits`.

## Supported Wan models

| Model ID | Type | Endpoints | Best for |
| - | - | - | - |
| `wan2.7-i2v` | Video | `/v1/video/generations` | Image-to-video generation |
| `wan2.7-image` | Image | `/v1/images/generations`, `/v1/images/edits` | Image generation and editing |
| `wan2.7-image-pro` | Image | `/v1/images/generations`, `/v1/images/edits` | Higher-quality image and image-to-video work |
| `wan2.7-r2v` | Video | `/v1/video/generations` | Reference-to-video generation |
| `wan2.7-t2v` | Video | `/v1/video/generations` | Text-to-video generation |
| `wan3.0-video` | Video | `/v1/video/generations` | Text-, image- and reference-to-video, editing and extension, up to 30 s |

Current prices for these models are on [aisa.one/models](https://aisa.one/models).

`wan3.0-video` is a single model for text-to-video, first-frame and first-and-last-frame image-to-video, reference-to-video, video editing and video extension, with output up to 30 seconds. The Wan 2.7 video models are split by input: `t2v` text-to-video, `i2v` image-to-video, `r2v` reference-to-video.

## Official DashScope API compatibility

| | Official DashScope | AIsa |
| - | - | - |
| Base URL | `https://dashscope-intl.aliyuncs.com/api/v1` | `https://api.aisa.one/v1/dashscope/api/v1` |
| API key | Model Studio API key | AIsa API key |

Paths, request bodies, responses and error codes are the official ones; see the [Wan video generation API](https://www.alibabacloud.com/help/en/model-studio/video-generate-edit-model/). This covers the Wan video models: `wan3.0-video`, `wan2.7-t2v`, `wan2.7-i2v` and `wan2.7-r2v`.

```python theme={null}
import os

import dashscope
from dashscope import VideoSynthesis

dashscope.base_http_api_url = "https://api.aisa.one/v1/dashscope/api/v1"
dashscope.api_key = os.environ["AISA_API_KEY"]

task = VideoSynthesis.async_call(
    model="wan3.0-video",
    prompt="A paper boat drifting across a calm lake at sunrise",
)
result = VideoSynthesis.wait(task)
print(result.output.task_status, result.output.video_url)
```

Not supported: listing and cancelling tasks, and temporary file uploads. Pass images, video and audio as public URLs (images can also be Base64); `oss://` temporary files and local files (`file://`) do not work.

## Resolution

The default resolution follows the API you call and is what you are billed for: `1080P` on the DashScope API, as on the official API, and `720P` on the AIsa video API. Set `resolution` to choose it. Wan 3.0 and Wan 2.7 requests that include `size` are rejected before anything is charged, because these models do not use `size` to choose the output resolution.

## Common choices

| Need | Use |
| - | - |
| One model for every video input, up to 30 seconds | `wan3.0-video` |
| Text-, image- or reference-to-video | `wan2.7-t2v`, `wan2.7-i2v`, or `wan2.7-r2v` |
| Image generation/editing | `wan2.7-image-pro` or `wan2.7-image` |

## Data privacy

Wan requests through AIsa are processed under AIsa's Alibaba Cloud Key Account enterprise agreement. For compliance documentation, [contact us](mailto:developer@aisa.one).

## Next

* [Qwen models](https://aisa.one/docs/models/qwen.md)
* [Model Catalog](https://aisa.one/docs/guides/models.md)
* [AI model pricing](https://aisa.one/docs/guides/pricing.md#models)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.