> ## 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

# Qwen and Wan API - Access Alibaba Models via AIsa

> Current AIsa guide to Alibaba Qwen and Wan model IDs and endpoints, including qwen3.8-max, qwen3.7-max, qwen-flash, Qwen VL, Qwen Coder, Wan image models, and translation models.

AIsa is an Alibaba Cloud Qwen Key Account Partner. Use one AIsa API key to access Qwen text, coding, vision, audio, video-understanding, translation, and Wan image models through the same gateway as your other LLMs.

Qwen text, coding, vision, and translation models use `POST /v1/chat/completions`. Wan image models use `POST /v1/images/generations` and `POST /v1/images/edits` and are billed per request; Wan video models are asynchronous through `POST /v1/video/generations` and are billed per output second.

## Supported Alibaba models

| Model ID | Type | Endpoints | Best for |
| - | - | - | - |
| `qwen3-coder-flash` | Text | `/v1/chat/completions`, `/v1/responses` | Fast coding throughput |
| `qwen3-vl-plus` | Text | `/v1/chat/completions`, `/v1/responses` | Stronger document and spatial vision |
| `qwen3.6-plus` | Text | `/v1/chat/completions`, `/v1/responses` | Long-context Chinese/bilingual work |
| `qwen3.6-plus-2026-04-02` | Text | `/v1/chat/completions`, `/v1/responses` | Pinned Qwen 3.6 Plus route |
| `qwen3.7-flash` | Text | `/v1/chat/completions`, `/v1/responses` | Fast Qwen 3.7 route |
| `qwen3.7-flash-2026-07-15` | Text | `/v1/chat/completions`, `/v1/responses` | Pinned snapshot of `qwen3.7-flash` |
| `qwen3.7-max` | Text | `/v1/chat/completions`, `/v1/responses` | Frontier Qwen reasoning and agentic coding |
| `qwen3.7-max-2026-06-08` | Text | `/v1/chat/completions`, `/v1/responses` | Pinned Qwen 3.7 Max route |
| `qwen3.7-plus` | Text | `/v1/chat/completions`, `/v1/responses` | Lower-cost Qwen 3.7 route |
| `qwen3.8-max` | Text | `/v1/chat/completions`, `/v1/responses` | Newest Qwen Max generation |
| `qwen-flash` | Text | `/v1/chat/completions`, `/v1/responses` | High-volume multimodal work |
| `qwen-mt-flash` | Text | `/v1/chat/completions`, `/v1/responses` | Fast translation |
| `qwen-mt-lite` | Text | `/v1/chat/completions`, `/v1/responses` | Lightweight translation |
| `qwen-plus-2025-12-01` | Text | `/v1/chat/completions` | General multimodal applications |
| `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 |

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

Video models are asynchronous: submit the job to `POST /v1/video/generations`, then poll `/v1/video/generations/{task_id}`.

## Quickstart

```python theme={null}
from openai import OpenAI

client = OpenAI(api_key="YOUR_AISA_API_KEY", base_url="https://api.aisa.one/v1")

response = client.chat.completions.create(
    model="qwen3.7-max",
    messages=[{"role": "user", "content": "Plan a refactor for this Python service."}]
)
print(response.choices[0].message.content)
```

## Common choices

| Need | Use |
| - | - |
| Cheapest high-volume text/multimodal | `qwen-flash` |
| Dedicated translation | `qwen-mt-flash` or `qwen-mt-lite` |
| Fast coding | `qwen3-coder-flash` |
| Maximum Qwen coding capability | `qwen3.7-max` |
| Long-context reasoning | `qwen3.7-max` or `qwen3.6-plus` |
| Vision/document/video work | `qwen3-vl-plus` |
| Image generation/editing | `wan2.7-image-pro` or `wan2.7-image` |
| Video generation | `wan2.7-t2v`, `wan2.7-i2v`, or `wan2.7-r2v` |

## Data privacy

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

## Next

* [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.