Qwen-Image-2.1-Turbo

Released
2026-10-09
Last refreshed
2026-10-09
Status
Researched today
Open weightsCommercial use: non-commercialMultimodalVisionImageMultimodalOpen Source
Alibaba releases · 52 in the last 12 months · this family litChangelog →
Specifications
Released
2026-10-09
Parameters
7B
Architecture
Diffusion Transformer
Specialization
image-generation
Openness
Open weights
License
Qwen Research LicenseCommercial use: non-commercial
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by
Alibaba

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · Alibaba Cloud PAI-EAS

Providers(1)
Alibaba Cloud PAI-EAS
View 1 provider route
Links
Website HuggingFace

About

Qwen-Image-2.1-Turbo is an accelerated checkpoint of Qwen-Image-2.1, released by Alibaba's Qwen team on 9 October 2026. It keeps the same 7B visual generation architecture and handles both text-to-image generation and image editing, but needs only 8 denoising steps; the recommended sampling schedule ships with the checkpoint, generation uses CFG 1 by default, and prefix KV caching reuses text and reference-image context across steps. It inherits Qwen-Image-2.1's features, including native transparent (RGBA) images and editing with multiple reference images and local controls, at resolutions up to about 2K per side.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Alibaba Cloud PAI-EAS--
ServerlessPartial

Capabilities

VisionMultimodal

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

Qwen-Image-2.1-TurboQwen/Qwen-Image-2.1-Turboqwen-image-2.1-turbo