Qwen and Wan API - Access Alibaba Models via AIsa

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

Quickstart

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.

Overview

Model families

Qwen and Wan API - Access Alibaba Models via AIsa

Supported Alibaba models

Quickstart

Common choices

Data privacy

Next

​Supported Alibaba models

​Quickstart

​Common choices

​Data privacy

​Next

Supported Alibaba models

Quickstart

Common choices

Data privacy

Next