Models - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center

Flagship models

International (Singapore)

Flagship models	Qwen-Max Ideal for complex tasks. The most powerful model.	Qwen-Plus A balance of performance, speed, and cost.	Qwen-Flash Ideal for simple jobs. Fast and low-cost.	Qwen-Coder An excellent code model that excels at tool calling and environment interaction.
Maximum context window (Tokens)	262,144	1,000,000	1,000,000	1,000,000
Minimum input price (Million tokens)	$1.2	$0.4	$0.05	$0.3
Minimum output price (Million tokens)	$6	$1.2	$0.4	$1.5

Chinese Mainland (Beijing)

Flagship models	Qwen-Max Ideal for complex tasks. The most powerful model.	Qwen-Plus A balance of performance, speed, and cost.	Qwen-Flash Ideal for simple jobs. Fast and low-cost.	Qwen-Coder An excellent code model that excels at tool calling and environment interaction.
Maximum context window (Tokens)	262,144	1,000,000	1,000,000	1,000,000
Minimum input price (Million tokens)	$0.459	$0.115	$0.022	$0.144
Minimum output price (Million tokens)	$1.836	$0.287	$0.216	$0.574

Model overview

International (Singapore)

Category	Subcategory	Description
Text generation	General-purpose large language models	Qwen large language models: Commercial models (Qwen-Max, Qwen-Plus, Qwen-Flash), open-source models (Qwen3, Qwen2.5)
	Multimodal models	Visual understanding model Qwen-VL, visual reasoning model QVQ, omni-modal model Qwen-Omni, and real-time multi-modal model Qwen-Omni-Realtime
	Domain-specific models	Coder model, Translation model, Role-playing model
Image generation	Text-to-image	Qwen text-to-image: Excels at rendering complex text, especially in Chinese and English. Wan text-to-image: Generate exquisite images with a single sentence.
Image generation	Image editing	Qwen image editing: Supports Chinese and English prompts and lets you perform complex image and text editing operations such as style transfer, text modification, and object editing. Wan image editing: Generates or edits images. This feature is suitable for creating ID photos, e-commerce main images, model photos, and portraits in various styles (such as cartoon, Chinese style, and anime). It can also be used for image matting, generating backgrounds, modifying image elements, and more.
Speech synthesis and recognition	Speech synthesis (text-to-speech)	Qwen-TTS and Qwen-TTS-Realtime can be used for text-to-speech in scenarios such as intelligent voice customer service, audiobooks, in-car navigation, and educational tutoring.
Speech synthesis and recognition	Speech recognition and translation	Qwen-ASR-Realtime, Qwen-ASR, Qwen3-LiveTranslate-Flash-Realtime and Fun-ASR can perform speech-to-text for scenarios such as real-time meeting records, real-time live stream captions, and telephone customer service.
Video generation	Text-to-video	Generates high-quality videos with rich styles from a single sentence.
	Image-to-video	First-frame-to-video: Uses an input image as the first frame and generates a video based on a prompt. First-and-last-frame-to-video: Generates a smooth and dynamic video based on the provided first and last frames and a prompt. Multi-image-to-video: Generates a video by referencing the entity or background in one or more input images, combined with a prompt.
	General-purpose video editing	General-purpose video editing: Performs various video editing tasks based on input text, images, and videos. For example, it can generate a new video by extracting motion features from an input video and combining them with a prompt.
Embedding	Text embedding	Converts text into a set of numbers that represent the text. It is suitable for search, clustering, recommendation, and classification tasks.

Mainland China (Beijing)

Category	Subcategory	Description
Text generation	General-purpose large language models	Qwen large language models: commercial editions (Qwen-Max, Qwen-Plus, and Qwen-Flash) and open-source editions (Qwen3 and Qwen2.5) Third-party models: DeepSeek, Kimi
	Multimodal models	The visual understanding model Qwen-VL, the visual reasoning model QVQ, and the omni-modal model Qwen-Omni
	Domain-specific models	Code model, Mathematical model, Translation model, Data mining model, Research model, Intention recognition model, Role-playing model
Image generation	Text-to-image	Qwen text-to-image: Excels in complex text rendering, especially for Chinese and English text. Wan text-to-image: Suitable for generating certificate photos, e-commerce main images, model photos, and portraits in various styles (such as cartoon, Chinese style, and anime style).
Image generation	Image editing	General-purpose models: Qwen image editing: Supports Chinese and English prompts for complex image and text editing operations, such as style transfer, text modification, and object editing. Wan image editing: Generates or edits images. You can create certificate photos, E-commerce main images, model photos, and portraits in various styles, such as cartoon, Chinese style, and anime. You can also remove backgrounds, generate backgrounds, and change image elements. More models: Qwen Image Translation, OutfitAnyone
Speech synthesis and recognition	Speech synthesis (text-to-speech)	Qwen-TTS, Qwen-TTS-Realtime, and CosyVoice convert text to speech for scenarios such as voice-based customer service, audiobooks, in-car navigation, and educational tutoring.
Speech synthesis and recognition	Speech recognition and translation	Qwen-ASR-Realtime, Qwen-ASR, Fun-ASR, and Paraformer convert speech to text for scenarios such as real-time meeting transcription, real-time live stream captioning, and customer service calls.
Video editing and generation	Text-to-video	Generates high-quality videos with rich styles from a single sentence.
	Image-to-video	First-frame-to-video: Generates a video from an initial image and a prompt. First-and-last-frame-to-video: Generates a video with a natural transition based on the first and last frame images and a prompt. Multi-image-to-video: Generates a video from one or more images and a text prompt, based on the entities or backgrounds in the source images. Dance video generation: AnimateAnyone generates dance videos from a character image and an action video. Image + audio to generate lip-sync videos Wan-digital human generates video from a person's image and audio. It provides a wide and natural range of motion, supports various frame sizes such as full-body, half-body, and portrait, and is suitable for scenarios such as singing and performance. EMO uses a person's image and audio to generate video with highly expressive lip-syncing and facial expressions. It supports portrait and half-body shots and is ideal for close-up scenarios. LivePortrait uses a portrait image and an audio file and is ideal for voice narration scenarios. Emoji video generation: Emoji generates facial emoji videos from facial images and preset dynamic facial templates.
	General-purpose video editing	General video editing: Performs various video editing tasks based on text prompts, images, and videos. For example, you can generate a new video by extracting motion features from an input video and combining them with a text prompt. Video lip-syncing: VideoRetalk uses a person's video and audio and is ideal for scenarios such as short video production and video translation. Video style transfer: Video Style Repainting transforms videos into various styles, such as Japanese manga and American comics.
Embedding	Text embedding	Converts text into a set of numbers that represent the text. It is used for search, clustering, recommendation, and classification.
Embedding	Multimodal embedding	Converts text, images, and speech into a set of numbers. It is used for audio and video classification, image classification, and image-text retrieval.

Text generation - Qwen

The following are the Qwen commercial models. Compared to the open-source versions, the commercial models offer the latest capabilities and improvements.

The parameter sizes of the commercial models are not disclosed.

Each model is updated periodically. To use a fixed version, you can select a snapshot version. A snapshot version is typically maintained for one month after the release of the next snapshot version.

We recommend that you use the stable or latest version for more lenient rate limiting conditions.

Qwen-Max

The best-performing model in the Qwen series, suitable for complex, multi-step tasks. Usage | API reference | Try it online

International (Singapore)

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Input cost	Output cost	Free quota (Note)
			(Tokens)				(Million tokens)
qwen3-max Currently same capability as qwen3-max-2025-09-23 Batch calling half price	Stable	Non-thinking only	262,144	258,048	-	65,536	Tiered pricing, see the description below.		1 million tokens each Valid for 90 days after activation
qwen3-max-2025-09-23	Snapshot	Non-thinking only
qwen3-max-preview	Preview	Thinking			81,920	32,768
		Non-thinking			-	65,536

Billing for the models listed above is tiered based on the number of input tokens per request.

Input tokens per request	Input price (Million tokens) qwen3-max and qwen3-max-preview support context cache.	Output price (Million tokens)
0 < Tokens ≤ 32K	$1.2	$6
32K < Tokens ≤ 128K	$2.4	$12
128K < Tokens ≤ 252K	$3	$15

More models

Model	Version	Context window	Max input	Max output	Input cost	Output cost	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-max Currently has the same capabilities as qwen-max-2025-01-25	Stable	32,768	30,720	8,192	$1.6 Batch calls are half price.	$6.4 Batch calls are half price.	1 million tokens for input and output each Valid for 90 days after you activate Model Studio.
qwen-max-latest Always has the same capabilities as the latest snapshot version	Latest				$1.6	$6.4
qwen-max-2025-01-25 also known as qwen-max-0125 or Qwen2.5-Max	Snapshot

Chinese mainland (Beijing)

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Input cost	Output cost
			(Tokens)				(Million tokens)
qwen3-max Currently same capability as qwen3-max-2025-09-23 Batch calling half price	Stable	Non-thinking only	262,144	258,048	-	65,536	Tiered pricing, see the description below.
qwen3-max-2025-09-23	Snapshot	Non-thinking only
qwen3-max-preview	Preview	Thinking			81,920	32,768
		Non-thinking			-	65,536

Billing for the models listed above is tiered based on the number of input tokens per request.

Model	Input tokens per request	Input price (Million tokens)	Output price (Million tokens) Chain-of-thought + response
qwen3-max batch calls are half price Context cache discounts	0 < Tokens ≤ 32K	$0.459	$1.836
	32K < Tokens ≤ 128K	$0.918	$3.672
	128K < Tokens ≤ 252K	$1.377	$5.508
qwen3-max-2025-09-23	0 < Tokens ≤ 32K	$0.861	$3.441
	32K < Tokens ≤ 128K	$1.434	$5.735
	128K < Tokens ≤ 252K	$2.151	$8.602
qwen3-max-preview Context cache discounts	0 < Tokens ≤ 32K	$0.861	$3.441
	32K < Tokens ≤ 128K	$1.434	$5.735
	128K < Tokens ≤ 252K	$2.151	$8.602

More models

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-max Currently has the same capabilities as qwen-max-2024-09-19	Stable	32,768	30,720	8,192	$0.345	$1.377
qwen-max-latest Always has the same capabilities as the latest snapshot version	Latest	131,072	129,024
qwen-max-2025-01-25 also known as qwen-max-0125 or Qwen2.5-Max	Snapshot
qwen-max-2024-09-19 also known as qwen-max-0919		32,768	30,720		$2.868	$8.602
qwen-max-2024-04-28 also known as qwen-max-0428	Snapshot	8,000	6,000	2,000	CNY 0.04	CNY 0.12
qwen-max-2024-04-03 also known as qwen-max-0403

The thinking mode of qwen3-max-preview significantly improves overall inference capabilities and excels in agent programming, common sense reasoning, mathematics, science, and general tasks.

Qwen-Plus

A balanced model that offers performance, cost, and speed between those of Qwen-Max and Qwen-Flash. It is suitable for moderately complex tasks. Usage | API reference | Try it online | Deep thinking

International (Singapore)

Model

Version

Context window

Max input

Max output

Input cost

Output cost

Free quota

(Note)

(Tokens)

(Million tokens)

qwen-plus

Currently has the same capabilities as qwen-plus-2025-07-28

Part of the Qwen3 series

Stable

1,000,000

Thinking mode

995,904

Non-thinking mode

997,952

The default is 262,144. You can adjust this value using the max_input_tokens parameter.

32,768

Max chain-of-thought: 81,920

Tiered pricing applies. For more information, see the notes below the table.

1 million tokens for input and output each

Valid for 90 days after you activate Model Studio.

qwen-plus-latest

Currently has the same capabilities as qwen-plus-2025-07-28

Part of the Qwen3 series

Latest

Thinking mode

995,904

Non-thinking mode

997,952

qwen-plus-2025-09-11

Part of the Qwen3 series.

Snapshot

Thinking mode

995,904

Non-thinking mode

997,952

qwen-plus-2025-07-28

also known as qwen-plus-0728

Part of the Qwen3 series

qwen-plus-2025-07-14

also known as qwen-plus-0714

Part of the Qwen3 series

131,072

Thinking mode

98,304

Non-thinking mode

129,024

16,384

Max chain-of-thought: 38,912

$0.4

Thinking mode

Non-thinking mode

$1.2

qwen-plus-2025-04-28

also known as qwen-plus-0428

Part of the Qwen3 series

qwen-plus-2025-01-25

also known as qwen-plus-0125

129,024

8,192

$1.2

Billing for qwen-plus, qwen-plus-latest, qwen-plus-2025-09-11, and qwen-plus-2025-07-28 is tiered based on the number of input tokens per request.

Input tokens per request	Input price (Million tokens)	Mode	Output price (Million tokens)
0 < Tokens ≤ 256K	$0.4	Non-thinking mode	$1.2
0 < Tokens ≤ 256K	$0.4	Thinking mode	$4
256K < Tokens ≤ 1M	$1.2	Non-thinking mode	$3.6
256K < Tokens ≤ 1M	$1.2	Thinking mode	$12

Chinese mainland (Beijing)

Model

Version

Context window

Max input

Max output

Input cost

Output cost

(Tokens)

(Million tokens)

qwen-plus

Currently has the same capabilities as qwen-plus-2025-07-28

Part of the Qwen3 series

Stable

1,000,000

Thinking mode

995,904

Non-thinking mode

997,952

The default is 131,072. You can adjust this value using the max_input_tokens parameter.

32,768

Max chain-of-thought: 81,920

Tiered pricing applies. For more information, see the notes below the table.

qwen-plus-latest

Currently has the same capabilities as qwen-plus-2025-07-28

Part of the Qwen3 series

Latest

Thinking mode

995,904

Non-thinking mode

997,952

qwen-plus-2025-09-11

Part of the Qwen3 series

Snapshot

Thinking mode

995,904

Non-thinking mode

997,952

qwen-plus-2025-07-28

also known as qwen-plus-0728

Part of the Qwen3 series

qwen-plus-2025-07-14

also known as qwen-plus-0714

Part of the Qwen3 series

131,072

Thinking mode

98,304

Non-thinking mode

129,024

16,384

Max chain-of-thought: 38,912

$0.115

Thinking mode

$1.147

Non-thinking mode

$0.287

qwen-plus-2025-04-28

also known as qwen-plus-0428

Part of the Qwen3 series

Billing for qwen-plus, qwen-plus-latest, qwen-plus-2025-09-11, and qwen-plus-2025-07-28 is tiered based on the number of input tokens per request.

Input tokens per request	Input price (Million tokens)	Mode	Output price (Million tokens)
0 < Tokens ≤ 128K	$0.115	Non-thinking mode	$0.287
0 < Tokens ≤ 128K	$0.115	Thinking mode	$1.147
128K < Tokens ≤ 256K	$0.345	Non-thinking mode	$2.868
128K < Tokens ≤ 256K	$0.345	Thinking mode	$3.441
256K < Tokens ≤ 1M	$0.689	Non-thinking mode	$6.881
256K < Tokens ≤ 1M	$0.689	Thinking mode	$9.175

These models support both thinking and non-thinking modes. You can switch between them using the enable_thinking parameter. In addition, the models' capabilities are significantly improved:

Reasoning capabilities: In evaluations for math, code, and logical reasoning, the model significantly outperforms QwQ and other models of similar size without a reasoning mode. It achieves top-tier performance among models of its scale.
Human preference alignment: The model shows significant improvements in creative writing, role assumption, multi-turn conversation, and instruction following. Its general capabilities are significantly better than those of other models of similar size.
Agent capabilities: The model achieves industry-leading performance in both thinking and non-thinking modes and can accurately invoke external tools.
Multilingual capabilities: The model supports more than 100 languages and dialects. Its capabilities in multilingual translation, instruction understanding, and common-sense reasoning are significantly improved.
Response format: This version fixes response format issues from previous versions, such as incorrect Markdown formatting, premature truncation, and incorrect boxed output.

For the models listed above, if you enable thinking mode but no thought process is generated, you are charged based on the pricing for non-thinking mode.

More models

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-plus-2025-01-25 also known as qwen-plus-0125	Snapshot	131,072	129,024	8,192	$0.115	$0.287
qwen-plus-2025-01-12 also known as qwen-plus-0112
qwen-plus-2024-12-20 also known as qwen-plus-1220
qwen-plus-2024-11-27 also known as qwen-plus-1127
qwen-plus-2024-11-25 also known as qwen-plus-1125
qwen-plus-2024-09-19 also known as qwen-plus-0919
qwen-plus-2024-08-06 also known as qwen-plus-0806			128,000		$0.574	$1.721

Qwen-Flash

The fastest and most cost-effective model in the Qwen series, ideal for simple jobs. Qwen-Flash features flexible tiered pricing, making it more cost-effective than Qwen-Turbo. Usage | API reference | Try it online | Thinking mode

International (Singapore)

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Input cost	Output cost Chain-of-thought + Outputs	Free quota (Note)
			(Tokens)				(1,000 tokens)
qwen-flash Same capabilities as qwen-flash-2025-07-28 Part of the Qwen3 series. Batch calls are charged at half the standard price.	Stable	Thinking	1,000,000	995,904	81,920	32,768	Tiered pricing. See the description below the table.		1 million tokens each Valid for 90 days after activating Alibaba Cloud Model Studio.
		Non-thinking		997,952	-
qwen-flash-2025-07-28 Part of the Qwen3 series.	Snapshot	Thinking		995,904	81,920
		Non-thinking		997,952	-

Billing for the models listed above is tiered based on the number of input tokens per request. qwen-flash supports context cache and batch calls.

Input tokens per request	Input price (Million tokens)	Output price (Million tokens)
0< Tokens ≤256K	$0.05	$0.4
256K< Tokens ≤1M	$0.25	$2

Chinese mainland (Beijing)

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Input cost	Output cost Chain-of-thought + Outputs
			(Tokens)				(1,000 tokens)
qwen-flash Same capabilities as qwen-flash-2025-07-28 Part of the Qwen3 series	Stable	Thinking	1,000,000	995,904	81,920	32,768	Tiered pricing. See the description below the table.
		Non-thinking		997,952	-
qwen-flash-2025-07-28 Part of the Qwen3 series	Snapshot	Thinking		995,904	81,920
		Non-thinking		997,952	-

Billing for the models listed above is tiered based on the number of input tokens per request. qwen-flash supports context cache.

Input tokens per request	Input price (Million tokens)	Output price (Million tokens)
0< Tokens ≤128K	$0.022	$0.216
128K< Tokens ≤256K	$0.087	$0.861
256K< Tokens ≤1M	$0.173	$1.721

Qwen-Turbo

Qwen-Turbo will no longer be updated. We recommend replacing it with Qwen-Flash. Qwen-Flash uses flexible tiered pricing, which offers a more granular pricing model. Usage | API reference | Try it online | Deep thinking

International (Singapore)

Model	Version	Context window	Max input	Max output	Input cost	Output cost	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-turbo Currently has the same capabilities as qwen-turbo-2025-04-28 Part of the Qwen3 series	Stable	Thinking mode 131,072 Non-thinking mode 1,000,000	Thinking mode 98,304 Non-thinking mode 1,000,000	16,384 Max chain-of-thought is 38,912	$0.05 Batch calls are half price	Thinking mode: $0.5 Non-thinking mode: $0.2 Batch calls are half price	1 million tokens for each Validity: 90 days after you activate Alibaba Cloud Model Studio
qwen-turbo-latest Always has the same capabilities as the latest snapshot version Part of the Qwen3 series	Latest				$0.05	Thinking mode: $0.5 Non-thinking mode: $0.2
qwen-turbo-2025-04-28 Also known as qwen-turbo-0428 Part of the Qwen3 series	Snapshot
qwen-turbo-2024-11-01 Also known as qwen-turbo-1101		1,000,000	1,000,000	8,192		$0.2

Mainland China (Beijing)

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-turbo Currently has the same capabilities as qwen-turbo-2025-04-28 Part of the Qwen3 series	Stable	Thinking mode 131,072 Non-thinking mode 1,000,000	Thinking mode 98,304 Non-thinking mode 1,000,000	16,384 Max chain-of-thought is 38,912	$0.044	Thinking mode $0.431 Non-thinking mode $0.087
qwen-turbo-latest Always has the same capabilities as the latest snapshot version Part of the Qwen3 series	Latest
qwen-turbo-2025-07-15 Also known as qwen-turbo-0715 Part of the Qwen3 series	Snapshot
qwen-turbo-2025-04-28 Also known as qwen-turbo-0428 Part of the Qwen3 series

QwQ

The QwQ reasoning model is trained on the Qwen2.5 model and uses reinforcement learning to significantly improve its reasoning capabilities. The model's core metrics for math and code, such as AIME 24/25 and LiveCodeBench, and some of its general metrics, such as IFEval and LiveBench, are comparable to the full-performance version of DeepSeek-R1. Usage

Singapore

Model

Version

Context window

Max input

Max chain-of-thought

Max response

Input cost

Output cost

Free quota

(Note)

(Tokens)

(Million tokens)

qwq-plus

Stable

131,072

98,304

32,768

8,192

$0.8

$2.4

1 million tokens

Validity: Within 90 days after you activate Alibaba Cloud Model Studio.

Mainland China (Beijing)

Model	Version	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost
		(Tokens)				(Million tokens)
qwq-plus Same capabilities as qwq-plus-2025-03-05.	Stable	131,072	98,304	32,768	8,192	$0.230	$0.574
qwq-plus-latest Always has the same capabilities as the latest snapshot version.	Latest
qwq-plus-2025-03-05 Also known as qwq-plus-0305.	Snapshot

Qwen-Long

The Qwen-Long model has the longest context window in the Qwen series. It offers balanced performance at a low cost. This model is ideal for tasks such as long-text analysis, information extraction, summarization, classification, and tagging. Usage | Try it online

China (Beijing)

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-long-latest Always matches the capabilities of the latest snapshot version.	Stable	10,000,000	10,000,000	8,192	$0.072	$0.287
qwen-long-2025-01-25 Also known as qwen-long-0125.	Snapshot

Qwen-Omni

The Qwen-Omni model accepts combined inputs from multiple modalities, such as text, images, audio, and video, and generates responses in text or speech format. It provides a variety of expressive, human-like voices and supports audio output in multiple languages and dialects. You can use it in audio and video chat scenarios, such as for visual recognition, sentiment analysis, and education and training. Usage | API reference

Singapore

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Free quota (Note)
			(Tokens)
qwen3-omni-flash Currently has the same capabilities as qwen3-omni-flash-2025-09-15	Stable	Thinking mode	65,536	16,384	32,768	16,384	1 million tokens each (modality-agnostic) Valid for 90 days after you activate Model Studio
		Non-thinking mode		49,152	-
qwen3-omni-flash-2025-09-15 Also known as qwen3-omni-flash-0915	Snapshot	Thinking mode	65,536	16,384	32,768	16,384
		Non-thinking mode		49,152	-

After you use your free quota, the following billing rules apply to inputs and outputs. The billing is the same for both thinking mode and non-thinking mode. Audio output is not supported in thinking mode.

Input	Unit price (Million tokens)
Text	$0.43
Audio	$3.81
Image/Video	$0.78

Output

Unit price (Million tokens)

Text

$1.66 (when input contains only text)

$3.06 (when input contains images, videos, or audio)

Text + Audio

This item is not billed in thinking mode.

$15.11 (Audio)

The output text is not billed.

More models

Model	Version	Context window	Max input	Max output	Free quota (Note)
		(Tokens)
qwen-omni-turbo This version has the same capabilities as qwen-omni-turbo-2025-03-26.	Stable	32,768	30,720	2,048	1 million tokens each (modality-agnostic) Valid for 90 days after activating Model Studio.
qwen-omni-turbo-latest Always points to the latest snapshot version. Equivalent capabilities	Latest
qwen-omni-turbo-2025-03-26 Also known as qwen-omni-turbo-0326.	Snapshot

After you use your free quota for commercial models, the following billing rules apply to inputs and outputs:

Input	Unit price (Million tokens)
Text	$0.07
Audio	$4.44
Image/Video	$0.21

Output

Unit price (Million tokens)

Text

$0.27 (when the input contains only text)

$0.63 (when the input contains images, videos, or audio)

Text + Audio

$8.89 (Audio)

The text portion of the output is not billed.

Mainland China (Beijing)

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Free quota (Note)
			(Tokens)
qwen3-omni-flash Currently has the same capabilities as qwen3-omni-flash-2025-09-15	Stable	Thinking mode	65,536	16,384	32,768	16,384	No free quota
		Non-thinking mode		49,152	-
qwen3-omni-flash-2025-09-15 Also known as qwen3-omni-flash-0915	Snapshot	Thinking mode	65,536	16,384	32,768	16,384
		Non-thinking mode		49,152	-

After your free quota is used up, inputs and outputs are billed according to the following rules. The billing is the same for both thinking mode and non-thinking mode. Audio output is not supported in thinking mode.

Input	Unit price (Million tokens)
Text	$0.258
Audio	$2.265
Image/Video	$0.473

Output

Unit price (Million tokens)

Text

$0.989 (when input contains only text)

$1.821 (when input contains images, videos, or audio)

Text + audio

This item is not billed in thinking mode.

$8.974 (audio)

The output text is not billed.

More models

Model	Version	Context window	Max input	Max output	Free quota (Note)
		(Tokens)
qwen-omni-turbo This model currently has the same capabilities as qwen-omni-turbo-2025-03-26.	Stable	32,768	30,720	2,048	No free quota
qwen-omni-turbo-latest Always aligned with the latest snapshot Identical capabilities	Latest
qwen-omni-turbo-2025-03-26 Also known as qwen-omni-turbo-0326.	Snapshot
qwen-omni-turbo-2025-01-19 Also known as qwen-omni-turbo-0119.

Inputs and outputs are billed according to the following rules:

Input	Unit price (Million tokens)
Text	$0.058
Audio	$3.584
Image/Video	$0.216

Output

Unit price (Million tokens)

Text

$0.230 (for text-only input)

$0.646 (when the input includes images, audio, or videos)

Text + audio

$7.168 (audio)

The output text is not billed.

For example, a request with 1,000 text input tokens, 1,000 image input tokens, 1,000 text output tokens, and 1,000 audio output tokens costs $0.000058 (text input) + $0.000216 (image input) + $0.007168 (audio output).

The Qwen3-Omni-Flash model offers significant improvements over Qwen-Omni-Turbo, which is no longer updated:

It is a hybrid thinking model that supports both thinking and non-thinking modes. You can switch between the modes using the enable_thinking parameter. By default, thinking mode is disabled.
Audio output is not supported in thinking mode. In non-thinking mode, the audio output from the model has the following features:
- It supports 17 voices, an increase from the 4 supported by Qwen-Omni-Turbo.
- It supports 10 languages, an increase from the 2 supported by Qwen-Omni-Turbo.

Qwen-Omni-Realtime

Compared to Qwen Omni, these models support audio stream input. They have a built-in Voice Activity Detection (VAD) feature that automatically detects the start and end of user speech. Usage | Client events | Server events

International (Singapore)

Model	Version	Context window	Max input	Max output	Free quota (Note)
		(Tokens)
qwen3-omni-flash-realtime Equivalent to qwen3-omni-flash-realtime-2025-09-15	Stable	65,536	49,152	16,384	1 million tokens each, regardless of modality Valid for 90 days after you activate Model Studio
qwen3-omni-flash-realtime-2025-09-15	Snapshot

After the free quota is exhausted, the following billing rules apply to inputs and outputs:

Input	Unit price (Million tokens)
Text	$0.52
Audio	$4.57
Image	$0.94

Output

Unit price (Million tokens)

Text

$1.99 (when input contains only text)

$3.67 (when input contains images or audio)

Text + Audio

$18.13 (audio)

Text output is not billed.

More models

Model	Version	Context window	Max input	Max output	Free quota (Note)
		(Tokens)
qwen-omni-turbo-realtime Equivalent to qwen-omni-turbo-realtime-2025-05-08	Stable	32,768	30,720	2,048	1 million tokens, regardless of modality Valid for 90 days after you activate Model Studio
qwen-omni-turbo-realtime-latest Always equivalent to the latest snapshot version	Latest
qwen-omni-turbo-realtime-2025-05-08	Snapshot

After the free quota is exhausted, the following billing rules apply to inputs and outputs:

Input	Unit price (Million tokens)
Text	$0.270
Audio	$4.440
Image	$0.840

Output

Unit price (Million tokens)

Text

$1.070 (for text-only input)

$2.520 (for input that contains images or audio)

Text + Audio

$8.890 (for audio output)

The text output is not billed.

Mainland China (Beijing)

Model	Version	Context window	Max input	Max output	Free quota (Note)
		(Tokens)
qwen3-omni-flash-realtime Equivalent to qwen3-omni-flash-realtime-2025-09-15	Stable	65,536	49,152	16,384	No free quota
qwen3-omni-flash-realtime-2025-09-15	Snapshot

The following billing rules apply to inputs and outputs:

Input	Unit price (Million tokens)
Text	$0.315
Audio	$2.709
Image	$0.559

Output

Unit price (Million tokens)

Text

$1.19 (when the input contains only text)

$2.179 (when the input contains images or audio)

Text + audio

$10.766 (audio)

Text output is not billed.

More models

Model	Version	Context window	Max input	Max output	Free quota (Note)
		(Tokens)
qwen-omni-turbo-realtime Equivalent to qwen-omni-turbo-2025-05-08	Stable	32,768	30,720	2,048	No free quota
qwen-omni-turbo-realtime-latest Always equivalent to the latest snapshot version	Latest
qwen-omni-turbo-realtime-2025-05-08	Snapshot

The following billing rules apply to inputs and outputs:

Input	Unit price (Million tokens)
Text	$0.230
Audio	$3.584
Image	$0.861

Output

Unit price (Million tokens)

Text

$0.918 (if the input contains only text)

$2.581 (if the input contains images or audio)

Text + Audio

$7.168 (audio)

Text output is not billed.

The Qwen3-Omni-Flash-Realtime model is recommended. It offers significantly improved capabilities compared to Qwen-Omni-Turbo-Realtime, which will no longer be updated. For audio output from the model:

It supports 17 voices. Qwen-Omni-Turbo-Realtime supports only 4.
It supports 10 languages. Qwen-Omni-Turbo-Realtime supports only 2.

QVQ

QVQ is a visual reasoning model that supports visual inputs and chain-of-thought outputs. It delivers superior performance in math, programming, visual analysis, creative tasks, and general tasks. Usage | Try it online

International (Singapore)

Model	Version	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost	Free quota (Note)
		(Tokens)				(Million tokens)
qvq-max Equivalent to qvq-max-2025-03-25.	Stable	131,072	106,496 Maximum of 16,384 tokens for a single image.	16,384	8,192	$1.2	$4.8	1 million input tokens and 1 million output tokens. Valid for 90 days after you activate Alibaba Cloud Model Studio.
qvq-max-latest Always equivalent to the latest snapshot version.	Latest
qvq-max-2025-03-25 Also known as qvq-max-0325.	Snapshot

Mainland China (Beijing)

Model	Version	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost
		(Tokens)				(Million tokens)
qvq-max Offers stronger visual reasoning and instruction-following capabilities than qvq-plus, providing optimal performance for more complex tasks. Has the same capabilities as qvq-max-2025-03-25.	Stable	131,072	106,496 Maximum of 16,384 for a single image.	16,384	8,192	$1.147	$4.588
qvq-max-latest Always has the same capabilities as the latest snapshot version.	Latest
qvq-max-2025-05-15 Also known as qvq-max-0515.	Snapshot
qvq-max-2025-03-25 Also known as qvq-max-0325.
qvq-plus Has the same capabilities as qvq-plus-2025-05-15.	Stable					$0.287	$0.717
qvq-plus-latest Always has the same capabilities as the latest snapshot version.	Latest
qvq-plus-2025-05-15 Also known as qvq-plus-0515.	Snapshot

Qwen-VL

Qwen-VL is a text generation model with visual understanding (image) capabilities. It not only performs Optical Character Recognition (OCR) but also provides further summarization and reasoning, such as extracting properties from product photos or solving problems shown in diagrams. Usage | API reference | Try it online

Qwen-VL models are billed based on the total number of input and output tokens. For more information about how image tokens are calculated, see Visual understanding.

International (Singapore)

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Input cost	Output cost (Chain-of-thought + Output)	Free quota (Note)
			(Tokens)				(Million tokens)
qwen3-vl-plus Same capabilities as qwen3-vl-plus-2025-09-23	Stable	thinking	262,144	258,048 Maximum of 16,384 tokens per image	81,920	32,768	Tiered pricing. For more information, see the description below the table.		1 million input tokens and 1 million output tokens Valid for 90 days after you activate Alibaba Cloud Model Studio.
		non-thinking		260,096 Maximum of 16,384 tokens per image	-
qwen3-vl-plus-2025-09-23	Snapshot	thinking		258,048 Maximum of 16,384 tokens per image	81,920
		non-thinking		260,096 Maximum of 16,384 tokens per image	-
qwen3-vl-flash Same capabilities as qwen3-vl-flash-2025-10-15	Stable	thinking		258,048 Maximum of 16,384 tokens per image	81,920
		non-thinking		260,096 Maximum of 16,384 tokens per image	-
qwen3-vl-flash-2025-10-15	Snapshot	thinking		258,048 Maximum of 16,384 tokens per image	81,920
		non-thinking		260,096 Maximum of 16,384 tokens per image	-

The models listed above use tiered pricing based on the number of input tokens per request. The input and output prices are the same for both thinking and non-thinking modes.

qwen3-vl-plus series

Input tokens per request	Input price (Million tokens)	Output price (Million tokens)
0 < Tokens ≤ 32K	$0.20	$1.60
32K < Tokens ≤ 128K	$0.30	$2.40
128K < Tokens ≤ 256K	$0.60	$4.80

qwen3-vl-flash series

Input tokens per request	Input price (Million tokens)	Output price (Million tokens)
0 < Tokens ≤ 32K	$0.05	$0.40
32K < Tokens ≤ 128K	$0.075	$0.60
128K < Tokens ≤ 256K	$0.12	$0.96

More models

Qwen-VL-Max

Qwen-VL-Max performs better than Qwen-VL-Plus. The following models belong to the Qwen2.5-VL series.

Model	Version	Context window	Max input	Max output	Input cost	Output cost	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-vl-max Offers improved visual reasoning and instruction-following capabilities compared to qwen-vl-plus. Provides optimal performance for complex tasks. Same capabilities as qwen-vl-max-2025-08-13.	Stable	131,072	129,024 Maximum 16,384 per image.	8,192	$0.8 Half price for batch calls	$3.2 Half price for batch calls	1 million input tokens and 1 million output tokens. The validity period is 90 days after Model Studio is activated.
qwen-vl-max-latest Always provides the same capabilities as the latest snapshot version.	Latest				$0.8	$3.2
qwen-vl-max-2025-08-13 Also known as qwen-vl-max-0813. Provides comprehensive improvements in visual understanding, with significantly enhanced math, reasoning, object detection, and multilingual processing capabilities.	Snapshot
qwen-vl-max-2025-04-08 Also known as qwen-vl-max-0408. A Qwen2.5-VL series model with an expanded 128k context window and significantly enhanced math and reasoning capabilities.

Qwen-VL-Plus

Qwen-VL-Plus offers a balance between performance and cost. The following models belong to the Qwen2.5-VL series.

Model	Version	Context window	Max input	Max output	Input cost	Output cost	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-vl-plus Same capabilities as qwen-vl-plus-2025-08-15.	Stable	131,072	129,024 Maximum of 16,384 per image.	8,192	$0.21 Half-price for batch calls	$0.63 Half-price for batch calls	1 million input tokens and 1 million output tokens Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen-vl-plus-latest Always has the same capabilities as the latest snapshot version.	Latest				$0.21	$0.63
qwen-vl-plus-2025-08-15 Also known as qwen-vl-plus-0815. Features significant improvements in object detection, localization, and multilingual processing.	Snapshot
qwen-vl-plus-2025-05-07 Also known as qwen-vl-plus-0507. Features significantly improved understanding of math, reasoning, and content from surveillance videos.
qwen-vl-plus-2025-01-25 Also known as qwen-vl-plus-0125. A Qwen2.5-VL series model with an expanded 128k context window and significantly enhanced image and video understanding.

Mainland China (Beijing)

Model	Version	Mode	Context window	Max input	Max chain-of-thought	Max output	Input cost	Output cost	Free quota (Note)
			(Tokens)				(Million tokens)
qwen3-vl-plus Same capabilities as qwen3-vl-plus-2025-09-23	Stable	thinking	262,144	258,048 Maximum of 16,384 tokens per image	81,920	32,768	Tiered pricing. For more information, see the description below the table.		No free quota
		non-thinking		260,096 Maximum of 16,384 tokens per image	-
qwen3-vl-plus-2025-09-23	Snapshot	thinking		258,048 Maximum of 16,384 tokens per image	81,920
		non-thinking		260,096 Maximum of 16,384 tokens per image	-
qwen3-vl-flash Same capabilities as qwen3-vl-flash-2025-10-15	Stable	thinking		258,048 Maximum of 16,384 tokens per image	81,920
		non-thinking		260,096 Maximum of 16,384 tokens per image	-
qwen3-vl-flash-2025-10-15	Snapshot	thinking		258,048 Maximum of 16,384 tokens per image	81,920
		non-thinking		260,096 Maximum of 16,384 tokens per image	-

The models listed above use tiered pricing based on the number of input tokens per request. The input and output prices are the same for both thinking and non-thinking modes.

qwen3-vl-plus series

Input tokens per request	Input price (Million tokens)	Output price (Million tokens)
0 < Tokens ≤ 32K	$0.143353	$1.433525
32K < Tokens ≤ 128K	$0.215029	$2.150288
128K < Tokens ≤ 256K	$0.430058	$4.300576

qwen3-vl-flash series

Input tokens per request	Input price (per 1M tokens)	Output price (per 1M tokens)
0 < Tokens ≤ 32K	$0.022	$0.215
32K < Tokens ≤ 128K	$0.043	$0.43
128K < Tokens ≤ 256K	$0.086	$0.859

More models

Qwen-VL-Max series

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-vl-max Offers improved visual reasoning and instruction-following capabilities compared to qwen-vl-plus and delivers optimal performance for complex tasks. Same capabilities as qwen-vl-max-2025-08-13.	Stable	131,072	129,024 Maximum of 16,384 per image	8,192	$0.23	$0.574
qwen-vl-max-latest Provides the same capabilities as the latest snapshot version.	Latest
qwen-vl-max-2025-08-13 Also known as qwen-vl-max-0813. Features comprehensive improvements in visual understanding and significantly enhanced capabilities for math, reasoning, object detection, and multilingual processing.	Snapshot
qwen-vl-max-2025-04-08 Also known as qwen-vl-max-0408. Enhanced math and reasoning capabilities.					$0.431	$1.291
qwen-vl-max-2025-04-02 Also known as qwen-vl-max-0402. Significantly improves accuracy in solving complex math problems.
qwen-vl-max-2025-01-25 Also known as qwen-vl-max-0125. This version is an upgrade to the Qwen2.5-VL series, featuring an expanded context window of 128k and significantly enhanced image and video understanding.
qwen-vl-max-2024-12-30 Also known as qwen-vl-max-1230.		32,768	30,720 Maximum of 16,384 per image	2,048	$0.431	$1.291
qwen-vl-max-2024-11-19 Also known as qwen-vl-max-1119.
qwen-vl-max-2024-10-30 Also known as qwen-vl-max-1030.					$2.868
qwen-vl-max-2024-08-09 Also known as qwen-vl-max-0809.

Qwen-VL-Plus series

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-vl-plus Offers the same capabilities as qwen-vl-plus-2025-08-15.	Stable	131,072	129,024 Maximum of 16,384 tokens per image.	8,192	$0.115	$0.287
qwen-vl-plus-latest Always has the same capabilities as the latest snapshot version.	Latest
qwen-vl-plus-2025-08-15 Also known as qwen-vl-plus-0815. Provides significant improvements in object detection, localization, and multilingual processing.	Snapshot
qwen-vl-plus-2025-07-10 Also known as qwen-vl-plus-0710. Further improves the understanding of content from surveillance videos.		32,768	30,720 Maximum of 16,384 tokens per image.		$0.022	$0.216
qwen-vl-plus-2025-05-07 Also known as qwen-vl-plus-0507. Significantly improves the understanding of math, reasoning, and content from surveillance videos.		131,072	129,024 Maximum of 16,384 tokens per image.		$0.216	$0.646
qwen-vl-plus-2025-01-25 Also known as qwen-vl-plus-0125. Upgrades to the Qwen2.5-VL series, expands the context window to 128K, and significantly enhances image and video understanding.
qwen-vl-plus-2025-01-02 Also known as qwen-vl-plus-0102.		32,768	30,720 Maximum of 16,384 tokens per image.	2,048
qwen-vl-plus-2024-08-09 Also known as qwen-vl-plus-0809.

Qwen-OCR

The Qwen-OCR model is designed for text extraction. Compared to the Qwen-VL model, it specializes in extracting text from images of documents, tables, exam papers, and handwriting. It can recognize multiple languages, such as English, French, Japanese, Korean, German, Russian, and Italian. Usage | API reference | Try it online

International (Singapore)

Model

Version

Context window

Max input

Max output

Unit price

Free quota

(Note)

(tokens)

(Million tokens)

qwen-vl-ocr

Stable

34,096

30,000

A single graph can support up to 30,000.

4,096

$0.72

1 million input tokens and 1 million output tokens

Validity: The quota is valid for 90 days after you activate Alibaba Cloud Model Studio.

Mainland China (Beijing)

Model	Version	Context window	Max input	Max output	Input/output unit price
		(Tokens)			(Million tokens)
qwen-vl-ocr Offers the same capabilities as qwen-vl-ocr-2025-04-13.	Stable	34,096	30,000 Maximum of 30,000 for a single image.	4,096	$0.717
qwen-vl-ocr-latest Offers the same capabilities as the latest snapshot version.	Latest
qwen-vl-ocr-2025-04-13 Also known as qwen-vl-ocr-0413. Significantly improves text recognition and includes six built-in OCR tasks and features, such as custom prompts and image rotation correction.	Snapshot
qwen-vl-ocr-2024-10-28 Also known as qwen-vl-ocr-1028.	Snapshot

Qwen-Math

Qwen-Math is a language model designed for mathematical problem-solving. Usage | API reference | Try it online

Note

This model is available only in the China (Beijing) region.

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-math-plus Same capabilities as qwen-math-plus-2024-09-19.	Stable	4,096	3,072	3,072	$0.574	$1.721
qwen-math-plus-latest Same capabilities as the latest snapshot.	Latest
qwen-math-plus-2024-09-19 Also known as qwen-math-plus-0919.	Snapshot
qwen-math-plus-2024-08-16 Also known as qwen-math-plus-0816.
qwen-math-turbo Same capabilities as qwen-math-turbo-2024-09-19.	Stable				$0.287	$0.861
qwen-math-turbo-latest Same capabilities as the latest snapshot.	Latest
qwen-math-turbo-2024-09-19 Also known as qwen-math-turbo-0919.	Snapshot

Qwen-Coder

The latest Qwen3-Coder-Plus series models are Qwen code generation models built on Qwen3. They are powerful coding agents that excel at tool calling and environment interaction. These models can program autonomously and provide excellent coding and general-purpose capabilities. Usage | API reference | Try it online

International (Singapore)

Model	Version	Context window	Max input	Max output	Input cost (Million tokens)	Output cost (Million tokens)	Free quota (Note)
		Tokens			Per million tokens
qwen3-coder-plus Currently equivalent to qwen3-coder-plus-2025-07-22	Stable	1,000,000	997,952	65,536	Tiered pricing. See the description below the table.		1 million input tokens and 1 million output tokens Valid for 90 days after you activate Alibaba Cloud Model Studio
qwen3-coder-plus-2025-09-23	Snapshot
qwen3-coder-plus-2025-07-22	Snapshot
qwen3-coder-flash Currently equivalent to qwen3-coder-flash-2025-07-28	Stable
qwen3-coder-flash-2025-07-28	Snapshot

These models use tiered billing based on the number of input tokens per request.

qwen3-coder-plus series

The prices for qwen3-coder-plus, qwen3-coder-plus-2025-09-23, and qwen3-coder-plus-2025-07-22 are as follows. The qwen3-coder-plus model supports context cache. Input text that hits the implicit cache is billed at 20% of the unit price. Input text that hits the explicit cache is billed at 10% of the unit price.

Input tokens per request	Input cost (Million tokens)	Output cost (Million tokens)
0 < Tokens ≤ 32K	$1	$5
32K < Tokens ≤ 128K	$1.8	$9
128K < Tokens ≤ 256K	$3	$15
256K < Tokens ≤ 1M	$6	$60

qwen3-coder-flash series

The prices for qwen3-coder-flash and qwen3-coder-flash-2025-07-28 are as follows. The qwen3-coder-flash model supports context cache. Input text that hits the implicit cache is billed at 20% of the unit price. Input text that hits the explicit cache is billed at 10% of the unit price.

Input tokens per request	Input cost (Million tokens)	Output cost (Million tokens)
0 < Tokens ≤ 32K	$0.3	$1.5
32K < Tokens ≤ 128K	$0.5	$2.5
128K < Tokens ≤ 256K	$0.8	$4
256K < Tokens ≤ 1M	$1.6	$9.6

Mainland China (Beijing)

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen3-coder-plus Provides the same functionality as qwen3-coder-plus-2025-07-22.	Stable	1,000,000	997,952	65,536	Tiered pricing. See the description below the table.
qwen3-coder-plus-2025-09-23	Snapshot
qwen3-coder-plus-2025-07-22	Snapshot
qwen3-coder-flash Currently an alias for qwen3-coder-flash-2025-07-28	Stable
qwen3-coder-flash-2025-07-28	Snapshot

These models use tiered billing based on the number of input tokens per request.

qwen3-coder-plus series

Input tokens per request	Input cost (Million tokens)	Output cost (Million tokens)
0 < Tokens ≤ 32K	$0.574	$2.294
32K < Tokens ≤ 128K	$0.861	$3.441
128K < Tokens ≤ 256K	$1.434	$5.735
256K < Tokens ≤ 1M	$2.868	$28.671

qwen3-coder-flash series

Input tokens per request	Input cost (Million tokens)	Output cost (Million tokens)
0 < Tokens ≤ 32K	$0.144	$0.574
32K < Tokens ≤ 128K	$0.216	$0.861
128K < Tokens ≤ 256K	$0.359	$1.434
256K < Tokens ≤ 1M	$0.717	$3.584

More models

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Million tokens)
qwen-coder-plus Same functionality as qwen-coder-plus-2024-11-06	Stable	131,072	129,024	8,192	$0.502	$1.004
qwen-coder-plus-latest Same functionality as the latest snapshot version of qwen-coder-plus	Latest
qwen-coder-plus-2024-11-06 Also known as qwen-coder-plus-1106	Snapshot
qwen-coder-turbo Same functionality as qwen-coder-turbo-2024-09-19	Stable	131,072	129,024	8,192	$0.287	$0.861
qwen-coder-turbo-latest Same functionality as the latest snapshot version of qwen-coder-turbo	Latest
qwen-coder-turbo-2024-09-19 Also known as qwen-coder-turbo-0919	Snapshot

Qwen-MT

This flagship large translation model is a comprehensive upgrade to Qwen 3. It supports translation between 92 languages, including Chinese, English, Japanese, Korean, French, Spanish, German, Thai, Indonesian, Vietnamese, and Arabic. The model's performance and translation quality are significantly improved. It provides enhanced support for custom glossaries, format retention, and domain-specific prompts, resulting in more accurate and natural translations. Usage.

International (Singapore)

Model	Context window	Max input	Max output	Input cost	Output cost	Free quota View rules
	(Tokens)			(Million tokens)
qwen-mt-plus Part of Qwen3-MT	16,384	8,192	8,192	$2.46	$7.37	1 million tokens per model Expires 90 days after activating Alibaba Cloud Model Studio.
qwen-mt-flash Part of Qwen3-MT				$0.16	$0.49
qwen-mt-turbo Part of Qwen3-MT				$0.16	$0.49

Mainland China (Beijing)

Model	Context window	Max input	Max output	Input cost	Output cost
	(Tokens)			(Million tokens)
qwen-mt-plus Part of Qwen3-MT	16,384	8,192	8,192	$0.259	$0.775
qwen-mt-flash Part of Qwen3-MT				$0.101	$0.280
qwen-mt-turbo Part of Qwen3-MT				$0.101	$0.280

Qwen data mining model

The Qwen data mining model extracts structured information from documents for use in domains such as data annotation and content moderation. Usage | API reference

Note

Available only in the China (Beijing) region.

Model	Context window	Max input	Max output	Input cost	Output cost	Free quota
Model	(Tokens)			(Million tokens)		Free quota
qwen-doc-turbo	131,072	129,024	8,192	$0.087	$0.144	No free quota

Qwen deep research model

The Qwen deep research model breaks down complex problems, performs inference and analysis using web search, and generates research reports. Usage | API reference

Note

Available only in the China (Beijing) region.

Model	Context window	Max input	Max output	Input cost	Output cost
Model	(Tokens)			(Per 1,000 tokens)
qwen-deep-research	1,000,000	997,952	32,768	$0.007742	$0.023367

Text generation - Qwen open-source versions

In the model names, xxb indicates the parameter size. For example, qwen2-72b-instruct indicates a parameter size of 72 billion (72B).
Alibaba Cloud Model Studio supports invoking the open-source versions of Qwen. You do not need to deploy the models locally. For open-source versions, we recommend using the Qwen3 and Qwen2.5 models.

Qwen3

qwen3-next-80b-a3b-thinking, released in September 2025, supports only thinking mode. Compared to qwen3-235b-a22b-thinking-2507, it offers improved instruction-following capabilities and more concise summaries.

qwen3-next-80b-a3b-instruct, released in September 2025, supports only non-thinking mode. It offers enhanced Chinese comprehension, logical reasoning, and text generation capabilities compared to qwen3-235b-a22b-instruct-2507.

The qwen3-235b-a22b-thinking-2507 and qwen3-30b-a3b-thinking-2507 models, released in July 2025, support only thinking mode. They are upgraded versions of qwen3-235b-a22b (thinking mode) and qwen3-30b-a3b (thinking mode).

The qwen3-235b-a22b-instruct-2507 and qwen3-30b-a3b-instruct-2507 models, released in July 2025, support only non-thinking mode. They are upgraded versions of qwen3-235b-a22b (non-thinking mode) and qwen3-30b-a3b (non-thinking mode).

The Qwen3 models, released in April 2025, support both thinking and non-thinking modes. You can switch between the modes using the enable_thinking parameter. The Qwen3 models also feature significant capability enhancements:

Inference capabilities: In evaluations for math, code, and logical reasoning, the models significantly outperform QwQ and other non-reasoning models of a similar scale. Their performance is top-tier in the industry for models of their scale.
Human preference alignment: The models show major improvements in creative writing, role assumption, multi-turn conversation, and instruction following. Their general capabilities are significantly better than other models of a similar scale.
Agent capabilities: The models deliver industry-leading performance in both thinking and non-thinking modes and can perform precise external tool calling.

Multilingual capabilities: The models support over 100 languages and dialects. They show significant improvements in multilingual translation, instruction comprehension, and common-sense reasoning.

Supported languages

English

Simplified Chinese

Traditional Chinese

French

Spanish

Arabic. Uses the Arabic script and is the official language of many Arab countries.

Russian. Uses the Cyrillic script and is an official language in Russia and several other countries.

Portuguese. Uses the Latin script and is the official language of Portugal, Brazil, and other Portuguese-speaking countries.

German. Uses the Latin script and is an official language in countries such as Germany and Austria.

Italian. Uses the Latin script and is an official language of Italy, San Marino, and parts of Switzerland.

Dutch. Uses the Latin script and is an official language of the Netherlands, parts of Belgium (Flanders), and Suriname.

Danish. Uses the Latin script and is the official language of Denmark.

Irish. Uses the Latin script and is one of the official languages of Ireland.

Welsh. Uses the Latin script and is one of the official languages of Wales.

Finnish. Uses the Latin script and is the official language of Finland.

Icelandic. Uses the Latin script and is the official language of Iceland.

Swedish. Uses the Latin script and is the official language of Sweden.

Norwegian Nynorsk. Uses the Latin script and is one of the two official written standards for the Norwegian language, used alongside Norwegian Bokmål.

Norwegian Bokmål. Uses the Latin script and is the more widely used of the two official written standards for the Norwegian language.

Japanese. Uses Japanese characters and is the official language of Japan.

Korean. Uses Hangul and is the official language of South Korea and North Korea.

Vietnamese. Uses the Latin script and is the official language of Vietnam.

Thai. Uses the Thai script and is the official language of Thailand.

Indonesian. Uses the Latin script and is the official language of Indonesia.

Malay. Uses the Latin script and is a major language in Malaysia and several other countries.

Burmese. Uses the Myanmar script and is the official language of Myanmar.

Tagalog. Uses the Latin script and is one of the major languages of the Philippines.

Khmer. Uses the Khmer script and is the official language of Cambodia.

Lao. Uses the Lao script and is the official language of Laos.

Hindi. Uses the Devanagari script and is one of the official languages of India.

Bengali. Uses the Bengali script and is the official language of Bangladesh and the Indian state of West Bengal.

Urdu. Uses the Arabic script, is an official language of Pakistan, and is also spoken in India.

Nepali. Uses the Devanagari script and is the official language of Nepal.

Hebrew. Uses the Hebrew script and is the official language of Israel.

Turkish. Uses the Latin script and is the official language of Türkiye and Northern Cyprus.

Persian. Uses the Arabic script and is an official language in countries such as Iran and Tajikistan.

Polish. Uses the Latin script and is the official language of Poland.

Ukrainian. Uses the Cyrillic script and is the official language of Ukraine.

Czech. Uses the Latin script and is the official language of the Czech Republic.

Romanian. Uses the Latin script and is the official language of Romania and Moldova.

Bulgarian. Uses the Cyrillic script and is the official language of Bulgaria.

Slovak. Uses the Latin script and is the official language of Slovakia.

Hungarian. Uses the Latin script and is the official language of Hungary.

Slovenian. Uses the Latin script and is the official language of Slovenia.

Latvian. Uses the Latin script and is the official language of Latvia.

Estonian. Uses the Latin script and is the official language of Estonia.

Lithuanian. Uses the Latin script and is the official language of Lithuania.

Belarusian. Uses the Cyrillic script and is one of the official languages of Belarus.

Greek. Uses the Greek alphabet and is the official language of Greece and Cyprus.

Croatian. Uses the Latin script and is the official language of Croatia.

Macedonian. Uses the Cyrillic script and is the official language of North Macedonia.

Maltese. Uses the Latin script and is an official language of Malta.

Serbian. Uses the Cyrillic script and is the official language of Serbia.

Bosnian. Uses the Latin script and is one of the official languages of Bosnia and Herzegovina.

Georgian. Uses the Georgian script and is the official language of Georgia.

Armenian. Uses the Armenian alphabet and is the official language of Armenia.

North Azerbaijani. Uses the Latin script and is the official language of Azerbaijan.

Kazakh. Uses the Cyrillic script and is an official language of Kazakhstan.

Northern Uzbek. Uses the Latin script and is the official language of Uzbekistan.

Tajik. Uses the Cyrillic script and is the official language of Tajikistan.

Swahili. Uses the Latin script and is a lingua franca or an official language in many East African countries.

Afrikaans. Uses the Latin script and is primarily spoken in South Africa and Namibia.

Cantonese. Uses Traditional Chinese characters and is the primary language spoken in Guangdong Province, Hong Kong, and Macao.

Luxembourgish. Uses the Latin script and is an official language of Luxembourg. It is also spoken in parts of Germany.

Limburgish. Uses the Latin script and is primarily spoken in the Netherlands, Belgium, and parts of Germany.

Catalan. Uses the Latin script and is spoken in Catalonia and other parts of Spain.

Galician. Uses the Latin script and is primarily spoken in the Galicia region of Spain.

Asturian. Uses the Latin script and is primarily spoken in the Asturias region of Spain.

Basque. Uses the Latin script. It is an official language of the Basque Autonomous Community in Spain and is primarily spoken throughout the Basque Country of Spain and France.

Occitan. Uses the Latin script and is primarily spoken in the southern regions of France.

Venetian. Uses the Latin script and is primarily spoken in the Veneto region of Italy.

Sardinian. Uses the Latin script and is primarily spoken on the island of Sardinia in Italy.

Sicilian. Uses the Latin script and is primarily spoken on the island of Sicily in Italy.

Friulian. Uses the Latin script and is primarily spoken in Friuli-Venezia Giulia, Italy.

Lombard. Uses the Latin script and is primarily spoken in the Lombardy region of Italy.

Ligurian. Uses the Latin script and is primarily spoken in the Liguria region of Italy.

Faroese. Uses the Latin script and is the official language of the Faroe Islands.

Tosk Albanian. Uses the Latin script and is the southern dialect of Albanian.

Silesian. Uses the Latin script and is primarily spoken in Poland.

Bashkir. Uses the Cyrillic script and is primarily spoken in Bashkortostan, Russia.

Tatar. Uses the Cyrillic script and is primarily spoken in Tatarstan, Russia.

Mesopotamian Arabic. Uses the Arabic script and is primarily spoken in Iraq.

Najdi Arabic. Uses the Arabic script and is primarily spoken in the Najd region of Saudi Arabia.

Egyptian Arabic. Uses the Arabic script and is primarily spoken in Egypt.

Levantine Arabic. Uses the Arabic script and is primarily spoken in Syria and Lebanon.

Ta'izzi-Adeni Arabic. Uses the Arabic script and is primarily spoken in Yemen and the Hadhramaut region of Saudi Arabia.

Dari. Uses the Arabic script and is one of the official languages of Afghanistan.

Tunisian Arabic. Uses the Arabic script and is primarily spoken in Tunisia.

Moroccan Arabic. Uses the Arabic script and is primarily spoken in Morocco.

Kabuverdianu. Uses the Latin script and is primarily spoken in Cape Verde.

Tok Pisin. Uses the Latin script and is a major lingua franca in Papua New Guinea.

Eastern Yiddish. Uses the Hebrew script and is primarily spoken in Jewish communities.

Sindhi. Uses the Arabic script and is an official language of the Sindh province in Pakistan.

Sinhala. Uses the Sinhala script and is one of the official languages of Sri Lanka.

Telugu. Uses the Telugu script and is an official language of the Indian states of Andhra Pradesh and Telangana.

Punjabi. Uses the Gurmukhi script, is spoken in the Indian state of Punjab, and is an official language of India.

Tamil. Uses the Tamil script and is an official language of the Indian state of Tamil Nadu and Sri Lanka.

Gujarati. Uses the Gujarati script and is the official language of the Indian state of Gujarat.

Malayalam. Uses the Malayalam script and is an official language of the Indian state of Kerala.

Marathi. Uses the Devanagari script and is the official language of the Indian state of Maharashtra.

Kannada. Uses the Kannada script and is the official language of the Indian state of Karnataka.

Magahi. Uses the Devanagari script and is primarily spoken in the Indian state of Bihar.

Oriya. Uses the Odia script and is one of the official languages of the Indian state of Odisha.

Awadhi. Uses the Devanagari script and is primarily spoken in the Indian state of Uttar Pradesh.

Maithili. Uses the Devanagari script, is spoken in the Indian state of Bihar and the Terai plains of Nepal, and is an official language of India.

Assamese. Uses the Bengali script and is an official language of the Indian state of Assam.

Chhattisgarhi. Uses the Devanagari script and is primarily spoken in the Indian state of Chhattisgarh.

Bhojpuri. Uses the Devanagari script and is spoken in parts of India and Nepal.

Minangkabau. Uses the Latin script and is primarily spoken on the island of Sumatra in Indonesia.

Balinese. Uses the Latin script and is primarily spoken on the island of Bali in Indonesia.

Javanese. Uses the Latin script, although the Javanese script is also traditionally used. It is widely spoken on the island of Java in Indonesia.

Banjar. Uses the Latin script and is primarily spoken on the island of Kalimantan in Indonesia.

Sundanese. Uses the Latin script, although the Sundanese script is also traditionally used. It is primarily spoken in the western part of the island of Java in Indonesia.

Cebuano. Uses the Latin script and is primarily spoken in the Cebu region of the Philippines.

Pangasinan. Uses the Latin script and is primarily spoken in the Pangasinan province of the Philippines.

Iloko. Uses the Latin script and is primarily spoken in the Philippines.

Waray (Philippines). Uses the Latin script and is primarily spoken in the Philippines.

Haitian Creole. Uses the Latin script and is one of the official languages of Haiti.

Papiamento. Uses the Latin script and is primarily spoken in Caribbean regions such as Aruba and Curaçao.

Response format fixes: This update fixes response format issues from previous versions, such as incorrect Markdown, truncated responses, and incorrect boxed output.

The open-source Qwen3 models released in April 2025 do not support non-streaming output in thinking mode.

If an open-source Qwen3 model is in thinking mode but does not output a thought process, it is billed at the non-thinking mode rate.

Thinking mode | Non-thinking mode | Usage

International (Singapore)

Model	Mode	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost	Free quota (Note)
Model	Mode	(Tokens)				(Million tokens)		Free quota (Note)
qwen3-next-80b-a3b-thinking	Thinking only	131,072	126,976	81,920	32,768	$0.15	$1.2	1 million tokens Valid for 90 days after you activate Alibaba Cloud Model Studio
qwen3-next-80b-a3b-instruct	Non-thinking only		129,024	-		$0.15	$1.2
qwen3-235b-a22b-thinking-2507	Thinking only		126,976	81,920		$0.23	$2.3
qwen3-235b-a22b-instruct-2507	Non-thinking only		129,024	-		$0.23	$0.92
qwen3-30b-a3b-thinking-2507	Thinking only		126,976	81,920		$0.2	$2.4
qwen3-30b-a3b-instruct-2507	Non-thinking only		129,024	-		$0.2	$0.8
qwen3-235b-a22b This model and the following models were released in April 2025.	Non-thinking mode		129,024	-	16,384	$0.7	$2.8
	Thinking mode		98,304	38,912		$0.7	$8.4
qwen3-32b	Non-thinking mode		129,024	-		$0.16	$0.64
qwen3-32b	Thinking mode		98,304	38,912		$0.16	$0.64
qwen3-30b-a3b	Non-thinking mode		129,024	-		$0.2	$0.8
qwen3-30b-a3b	Thinking mode		98,304	38,912		$0.2	$2.4
qwen3-14b	Non-thinking mode		129,024	-	8,192	$0.35	$1.4
qwen3-14b	Thinking mode		98,304	38,912		$0.35	$4.2
qwen3-8b	Non-thinking mode		129,024	-		$0.18	$0.7
qwen3-8b	Thinking mode		98,304	38,912		$0.18	$2.1
qwen3-4b	Non-thinking mode		129,024	-		$0.11	$0.42
qwen3-4b	Thinking mode		98,304	38,912			$1.26
qwen3-1.7b	Non-thinking mode	32,768	30,720	-			$0.42
qwen3-1.7b	Thinking mode		28,672	The total value cannot exceed 30,720.			$1.26
qwen3-0.6b	Non-thinking mode		30,720	-			$0.42
qwen3-0.6b	Thinking mode		28,672	The total of the value and the input cannot exceed 30,720.			$1.26

Mainland China (Beijing)

Model	Mode	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost
Model	Mode	(Tokens)				(Million tokens)
qwen3-next-80b-a3b-thinking	Thinking only	131,072	126,976	81,920	32,768	$0.144	$1.434
qwen3-next-80b-a3b-instruct	Non-thinking only		129,024	-		$0.144	$0.574
qwen3-235b-a22b-thinking-2507	Thinking only		126,976	81,920		$0.287	$2.868
qwen3-235b-a22b-instruct-2507	Non-thinking only		129,024	-		$0.287	$1.147
qwen3-30b-a3b-thinking-2507	Thinking only		126,976	81,920		$0.108	$1.076
qwen3-30b-a3b-instruct-2507	Non-thinking only		129,024	-		$0.108	$0.431
qwen3-235b-a22b	Non-thinking		129,024	-	16,384	$0.287	$1.147
qwen3-235b-a22b	Thinking		98,304	38,912		$0.287	$2.868
qwen3-32b	Non-thinking		129,024	-		$0.287	$1.147
qwen3-32b	Thinking		98,304	38,912		$0.287	$2.868
qwen3-30b-a3b	Non-thinking		129,024	-		$0.108	$0.431
qwen3-30b-a3b	Thinking		98,304	38,912		$0.108	$1.076
qwen3-14b	Non-thinking		129,024	-	8,192	$0.144	$0.574
qwen3-14b	Thinking		98,304	38,912		$0.144	$1.434
qwen3-8b	Non-thinking		129,024	-		$0.072	$0.287
qwen3-8b	Thinking		98,304	38,912		$0.072	$0.717
qwen3-4b	Non-thinking		129,024	-		$0.044	$0.173
qwen3-4b	Thinking		98,304	38,912			$0.431
qwen3-1.7b	Non-thinking	32,768	30,720	-			$0.173
qwen3-1.7b	Thinking		28,672	The sum of input and chain-of-thought tokens must not exceed 30,720.			$0.431
qwen3-0.6b	Non-thinking		30,720	-			$0.173
qwen3-0.6b	Thinking		28,672	The sum of input and chain-of-thought tokens must not exceed 30,720.			$0.431

QwQ-Open-source

QwQ reasoning model trained on Qwen2.5-32B. Reinforcement learning has significantly improved its inference capabilities. Core metrics for math and code (AIME 24/25, LiveCodeBench) and some general metrics (IFEval, LiveBench) are on par with the full-power version of DeepSeek-R1. All metrics significantly exceed those of DeepSeek-R1-Distill-Qwen-32B, which is also based on Qwen2.5-32B. Usage | API reference

Note

This feature is only available in the China (Beijing) region.

Model	Context window	Max input	Max chain-of-thought	Max output	Input price	Output price
Model	(Tokens)				(Million tokens)
qwq-32b	131,072	98,304	32,768	8,192	$0.287	$0.861

QwQ-Preview

The qwq-32b-preview model is an experimental research model developed by the Qwen team in 2024. It focuses on enhancing AI reasoning capabilities, especially in math and programming. For more information about the limitations of the qwq-32b-preview model, see the QwQ official blog. Usage | API reference | Try it online

Note

This feature is only available in the China (Beijing) region.

Model	Context window	Max input	Max output	Input cost	Output cost
Model	(Tokens)			(Million tokens)
qwq-32b-preview	32,768	30,720	16,384	$0.287	$0.861

Qwen2.5

Qwen2.5 is a series of Qwen large language models. For Qwen2.5, we have released a series of base language models and instruction-tuned language models with parameter sizes ranging from 7 billion to 72 billion. Qwen2.5 includes the following improvements over Qwen2:

It is pre-trained on our latest large-scale dataset, which contains up to 18 trillion tokens.
Our specialized expert models in these fields have significantly increased the model's knowledge and greatly improved its coding and math capabilities.
It has significant improvements in following instructions, generating long text (over 8K tokens), understanding structured data (such as tables), and generating structured output (especially JSON). It is more resilient to the diversity of system prompts, which enhances the implementation of role-play and conditional settings for chatbots.
It supports over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic.

Usage | API reference | Try it online

International (Singapore)

Model	Context window	Max input	Max output	Input price	Output price	Free quota
	(Tokens)			(Million tokens)
qwen2.5-14b-instruct-1m	1,008,192	1,000,000	8,192	$0.805	$3.22	1 million input and 1 million output tokens Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen2.5-7b-instruct-1m				$0.368	$1.47
qwen2.5-72b-instruct	131,072	129,024		$1.40	$5.60
qwen2.5-32b-instruct				$0.70	$2.80
qwen2.5-14b-instruct				$0.35	$1.40
Qwen2.5-7B-Instruct				$0.175	$0.700

Mainland China (Beijing)

Model	Context window	Max input	Max output	Input cost	Output cost
Model	(Tokens)			(Million tokens)
qwen2.5-14b-instruct-1m	1,000,000	1,000,000	8,192	$0.144	$0.431
qwen2.5-7b-instruct-1m	1,000,000	1,000,000		$0.072	$0.144
qwen2.5-72b-instruct	131,072	129,024		$0.574	$1.721
qwen2.5-32b-instruct				$0.287	$0.861
qwen2.5-14b-instruct				$0.144	$0.431
qwen2.5-7b-instruct				$0.072	$0.144
qwen2.5-3b-instruct	32,768	30,720		$0.044	$0.130
qwen2.5-1.5b-instruct				Free for a limited time
qwen2.5-0.5b-instruct				Free for a limited time

QVQ

The qvq-72b-preview model is an experimental research model developed by the Qwen team. It focuses on enhancing visual reasoning capabilities, especially in mathematical reasoning. For more information about the limitations of the qvq-72b-preview model, see the QVQ official blog. Usage | API reference

To have the model output the thinking process before the final answer, you can use the commercial version of the QVQ model.

Note

This feature is only available in the China (Beijing) region.

Model

Context window

Max input

Max output

Input Cost

Output cost

Tokens

Per million tokens

qvq-72b-preview

32,768

16,384

Maximum 16,384 tokens per image

16,384

$1.721

$5.161

Qwen-Omni

This is a new multimodal large model for understanding and generation, trained on Qwen2.5. It supports text, image, speech, and video inputs, and can generate text and speech simultaneously in a stream. The speed of multimodal content understanding is significantly improved. Usage | API reference

International (Singapore)

Model

Context window

Max input

Max output

Free quota

(Note)

(Tokens)

qwen2.5-omni-7b

32,768

30,720

2,048

1 million tokens (regardless of modality)

Valid for 90 days after activating Alibaba Cloud Model Studio.

After the free quota is used up, the following billing rules apply to inputs and outputs:

Input item	Price (Million tokens)
Text	$0.10
Audio	$6.76
Image/Video	$0.28

Output item

Price (Million tokens)

Text

$0.40 (if the input contains only text)

$0.84 (if the input contains images, audio, or video)

Text and audio

$13.51 (for the audio component)

The text portion of the output is not billed.

Mainland China (Beijing)

Model	Context window	Max input	Max output
Model	(Tokens)
qwen2.5-omni-7b	32,768	30,720	2,048

The billing rules for inputs and outputs are as follows:

Input	Price (Million tokens)
Text	$0.087
Audio	$5.448
Image or video	$0.287

Output

Price (Million tokens)

Text

$0.345 (if the input is text-only)

$0.861 (if the input includes images, audio, or video)

Text and audio

$10.895 (for the audio portion)

The text portion of the output is not billed.

Qwen3-Omni-Captioner

Qwen3-Omni-Captioner is an open-source model based on Qwen3-Omni. Without any prompts, it automatically generates accurate and comprehensive descriptions for complex audio, including speech, ambient sounds, music, and sound effects. It can identify speaker emotions, musical elements (such as style and instruments), and sensitive information, making it suitable for applications such as audio content analysis, security audits, intent recognition, and audio editing. Usage | API reference

Note

This model is available only in the Singapore region.

Model

Context window

Max input

Max output

Input cost

Output cost

Free quota

(Note)

(Tokens)

(Million tokens)

qwen3-omni-30b-a3b-captioner

65,536

32,768

$3.81

$3.06

1 million tokens

Validity: 90 days after you activate Alibaba Cloud Model Studio

Qwen-VL

This is the open-source version of Alibaba Cloud's Qwen-VL. Usage | API reference

The Qwen3-VL model offers significant improvements over Qwen2.5-VL:

Agent interaction: It operates computer and mobile phone interfaces, detects graphical user interface (GUI) elements, understands features, and invokes tools to perform tasks. It achieves top-tier performance in evaluations such as OS World.
Visual encoding: It generates code from images or videos. You can use this feature to create HTML, CSS, and JS code from design drafts or website screenshots.
Spatial intelligence: It supports 2D and 3D positioning and accurately determines object orientation, perspective changes, and occlusion relationships.
Long video understanding: It understands video content up to 20 minutes long and can pinpoint specific moments with second-level accuracy.
Deep thinking: It excels at capturing details and analyzing causality, achieving top-tier performance in evaluations such as MathVista and MMMU.
OCR: It supports 33 languages and performs more stably in scenarios that involve complex lighting, blur, or tilt. It also significantly improves recognition accuracy for rare characters, ancient script, and technical terms.
Supported languages
The model supports the following 33 languages: Chinese, Japanese, Korean, Indonesian, Vietnamese, Thai, English, French, German, Russian, Portuguese, Spanish, Italian, Swedish, Danish, Czech, Norwegian, Dutch, Finnish, Türkiye, Polish, Swahili, Romanian, Serbian, Greek, Kazakh, Uzbek, Cebuano, Arabic, Urdu, Persian, Hindi/Devanagari, and Hebrew.

International (Singapore)

Model	Mode	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost CoT + response	Free quota (Note)
Model	Mode	(Tokens)				(Million tokens)		Free quota (Note)
qwen3-vl-235b-a22b-thinking	Thinking only		126,976	81,920		$0.4	$4	1 million tokens each Valid for 90 days after Model Studio is activated.
qwen3-vl-235b-a22b-instruct	Non-thinking only		129,024	-		$0.4	$1.6
qwen3-vl-32b-thinking	Thinking only	131,072	126,976	81,920	32,768	$0.16	$0.64
qwen3-vl-32b-instruct	Non-thinking only		129,024	-		$0.16	$0.64
qwen3-vl-30b-a3b-thinking	Thinking only		126,976	81,920		$0.2	$2.4
qwen3-vl-30b-a3b-instruct	Non-thinking only		129,024	-		$0.2	$0.8
qwen3-vl-8b-thinking	Thinking only		126,976	81,920		$0.18	$2.1
qwen3-vl-8b-instruct	Non-thinking only		129,024	-		$0.18	$0.7

More models

Model	Context window	Max input	Max output	Input cost	Output cost	Free quota (Note)
	(Tokens)			(Million tokens)
qwen2.5-vl-72b-instruct	131,072	129,024 Maximum 16,384 per image	8,192	$2.8	$8.4	1 million tokens Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen2.5-vl-32b-instruct				$1.4	$4.2
qwen2.5-vl-7b-instruct				$0.35	$1.05
qwen2.5-vl-3b-instruct				$0.21	$0.63

Mainland China (Beijing)

Model	Mode	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost CoT + response	Free quota (Note)
Model	Mode	(Tokens)				(Million tokens)		Free quota (Note)
qwen3-vl-235b-a22b-thinking	Thinking only	131,072	126,976	81,920		$0.286705	$2.867051	No free quota
qwen3-vl-235b-a22b-instruct	Non-thinking only	131,072	129,024	-		$0.286705	$1.146820
qwen3-vl-32b-thinking	Thinking only	131,072	126,976	81,920	32,768	$0.287	$2.868
qwen3-vl-32b-instruct	Non-thinking only		129,024	-		$0.287	$1.147
qwen3-vl-30b-a3b-thinking	Thinking only		126,976	81,920		$0.108	$1.076
qwen3-vl-30b-a3b-instruct	Non-thinking only		129,024	-		$0.108	$0.431
qwen3-vl-8b-thinking	Thinking only		126,976	81,920		$0.072	$0.717
qwen3-vl-8b-instruct	Non-thinking only		129,024	-		$0.072	$0.287

More models

Model	Context window	Max input	Max output	Input cost	Output cost	Free quota (Note)
Model	(Tokens)			(Million tokens)		Free quota (Note)
qwen2.5-vl-72b-instruct	131,072	129,024 Maximum 16,384 per image	8,192	$2.294	$6.881	No free quota
qwen2.5-vl-32b-instruct				$1.147	$3.441
qwen2.5-vl-7b-instruct				$0.287	$0.717
qwen2.5-vl-3b-instruct				$0.173	$0.517
qwen2-vl-72b-instruct	32,768	30,720 Maximum 16,384 per image	2,048	$2.294	$6.881

Qwen-Math

This is a language model built on the Qwen model that is specialized for solving mathematical problems. Qwen2.5-Math supports Chinese and English and integrates multiple reasoning methods, including Chain of Thought (CoT), Program of Thought (PoT), and Tool-Integrated Reasoning (TIR). Usage | API reference | Try it online

Note

This feature is only available in the China (Beijing) region.

Model	Context window	Max input	Max output	Input cost	Output cost
	(Tokens)			(Million tokens)
qwen2.5-math-72b-instruct	4,096	3,072	3,072	$0.574	$1.721
qwen2.5-math-7b-instruct				$0.144	$0.287
qwen2.5-math-1.5b-instruct				Free for a limited time

Qwen-Coder

Qwen-Coder is an open source code model from Qwen. The latest Qwen3-Coder series has powerful Coding Agent capabilities. It excels at tool calling, environment interaction, and autonomous programming. The model combines excellent coding skills with general-purpose capabilities. Usage | API reference

International (Singapore)

Model	Context window	Max input	Max output	Input cost	Output cost	Free quota (Note)
	Token count
qwen3-coder-480b-a35b-instruct	262,144	204,800	65,536	Tiered pricing. See the description below the table.		1 million input tokens and 1 million output tokens Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen3-coder-30b-a3b-instruct

Billing for qwen3-coder-480b-a35b-instruct and qwen3-coder-30b-a3b-instruct is tiered based on the number of input tokens per request.

Model	Input tokens per request	Input cost (Million tokens)	Output cost (Million tokens)
qwen3-coder-480b-a35b-instruct	0 < Tokens ≤ 32K	$1.50	$7.50
	32K < Tokens ≤ 128K	$2.70	$13.50
	128K < Tokens ≤ 200K	$4.50	$22.50
qwen3-coder-30b-a3b-instruct	0 < Tokens ≤ 32K	$0.45	$2.25
	32K < Tokens ≤ 128K	$0.75	$3.75
	128K < Tokens ≤ 200K	$1.20	$6.00

Mainland China (Beijing)

Model	Context window	Max input	Max output	Input cost	Output cost
	(Tokens)			(Million tokens)
qwen3-coder-480b-a35b-instruct	262,144	204,800	65,536	Tiered pricing. See the description below.
qwen3-coder-30b-a3b-instruct
qwen2.5-coder-32b-instruct	131,072	129,024	8,192	$0.287	$0.861
qwen2.5-coder-14b-instruct
qwen2.5-coder-7b-instruct				$0.144	$0.287
qwen2.5-coder-3b-instruct	32,768	30,720		Limited-time free trial
qwen2.5-coder-1.5b-instruct
qwen2.5-coder-0.5b-instruct

Billing for qwen3-coder-480b-a35b-instruct and qwen3-coder-30b-a3b-instruct is tiered based on the number of input tokens per request.

Model	Input tokens per request	Input cost (Million tokens)	Output cost (Million tokens)
qwen3-coder-480b-a35b-instruct	0 < Tokens ≤ 32K	$0.861	$3.441
	32K < Tokens ≤ 128K	$1.291	$5.161
	128K < Tokens ≤ 200K	$2.151	$8.602
qwen3-coder-30b-a3b-instruct	0 < Tokens ≤ 32K	$0.216	$0.861
	32K < Tokens ≤ 128K	$0.323	$1.291
	128K < Tokens ≤ 200K	$0.538	$2.151

Text generation - Third-party models

DeepSeek

DeepSeek is a large language model launched by DeepSeek AI. API reference | Try it online

Note

This feature is only available in the China (Beijing) region.

Model	Context window	Max input	Max chain-of-thought	Max response	Input cost	Output cost
	(Tokens)				(Million tokens)
deepseek-v3.2-exp 685B full-power version	131,072	98,304	32,768	65,536	$0.287	$0.431
deepseek-v3.1 685B full-power version					$0.574	$1.721
deepseek-r1 685B full-power version				16,384		$2.294
deepseek-r1-0528 685B full-power version
deepseek-v3 671B full-power version		131,072	Not applicable		$0.287	$1.147
deepseek-r1-distill-qwen-1.5b Based on Qwen2.5-Math-1.5B	32,768	32,768	16,384	16,384	Limited-time free trial
deepseek-r1-distill-qwen-7b Based on Qwen2.5-Math-7B					$0.072	$0.144
deepseek-r1-distill-qwen-14b Based on Qwen2.5-14B					$0.144	$0.431
deepseek-r1-distill-qwen-32b Based on Qwen2.5-32B					$0.287	$0.861
deepseek-r1-distill-llama-8b Based on Llama-3.1-8B					Limited-time free trial
deepseek-r1-distill-llama-70b Based on Llama-3.3-70B

Kimi

Kimi-K2 is the first open-source trillion-parameter Mixture of Experts (MoE) model in China, provided by Moonshot AI. It activates 32 billion parameters and has excellent coding and tool-calling capabilities. Usage | Try it online

Note

This feature is only available in the China (Beijing) region.

Model	Context window	Max input	Max chain-of-thought	Max response	Input price	Output price
Model	(Tokens)				(Million tokens)
kimi-k2-thinking	262,144	229,376	32,768	16,384	$0.574	$2.294
Moonshot-Kimi-K2-Instruct	131,072	131,072	-	8,192	$0.574	$2.294

Image generation

Qwen text-to-image

The Qwen text-to-image model excels at complex text rendering, especially for Chinese and English text.Currently, qwen-image-plus has the same capabilities as qwen-image, but qwen-image-plus has a lower price.API reference

International (Singapore)

Model	Unit price	Free quota

qwen-image-plus	$0.03/image	Free quota: 100 images for each model Validity period: Within 90 days after you activate Alibaba Cloud Model Studio.
qwen-image	$0.035/image

Mainland China (Beijing)

Model	Unit price	Free quota

qwen-image-plus	$0.028671/image	No free quota
qwen-image	$0.035/image

Input prompt

Output image

Healing-style hand-drawn poster featuring three puppies playing with a ball on lush green grass, adorned with decorative elements such as birds and stars. The main title “Come Play Ball!” is prominently displayed at the top in bold, blue cartoon font. Below it, the subtitle “Come [Show Off Your Skills]!” appears in green font. A speech bubble adds playful charm with the text: “Hehe, watch me amaze my little friends next!” At the bottom, supplementary text reads: “We get to play ball with our friends again!” The color palette centers on fresh greens and blues, accented with bright pink and yellow tones to highlight a cheerful, childlike atmosphere.

Qwen image editing

The Qwen image editing model supports precise text editing in Chinese and English. It also supports operations such as color adjustment, detail enhancement, style transfer, adding or removing objects, and changing positions and actions. These features enable complex editing of images and text. API reference

International (Singapore)

Model	Unit price	Free quota

qwen-image-edit-plus	$0.03/image	Free quota: 100 images for each model Validity period: Within 90 days after you activate Alibaba Cloud Model Studio.
qwen-image-edit-plus-2025-10-30	$0.03/image
qwen-image-edit	$0.045/image

Mainland China (Beijing)

Model	Unit price	Free quota

qwen-image-edit-plus	$0.028671/image	No free quota
qwen-image-edit-plus-2025-10-30	$0.028671/image
qwen-image-edit	$0.043/image

dog_and_girl (1)

Original image

狗修改图

Make the person stand up and bend over to hold the front paw of the dog.

Original image

Replace the text 'HEALTH INSURANCE' on the letter blocks with '明天会更好'.

Original image

5out

Replace the dotted shirt with a light blue shirt.

Original image

6out

Change the background to Antarctica.

Original image

7out

Generate a cartoon profile picture of the person.

Original image

Remove the hair from the dinner plate.

Qwen image translation

The Qwen image translation model supports translating text from images in 11 languages into Chinese or English. It accurately preserves the original layout and content information and provides custom features such as term definition, sensitive word filtering, and image entity detection. API reference

Note

This feature is only available in the China (Beijing) region.

Model	Unit price	Free quota

qwen-mt-image	$0.000431/image	No free quota

Original image

Japanese

Portuguese

Arabic

Wan text-to-image

The Wan text-to-image model generates exquisite images from text. API reference | Try it online

International (Singapore)

Model	Description	Unit price	Free quota(Note) _{Validity period: Within 90 days after you activate Alibaba Cloud Model Studio.}
wan2.5-t2i-preview `Recommended`	Wan 2.5 preview. The single-side length limit is removed. You can freely select dimensions within the total pixel area and aspect ratio constraints.	$0.03/image	50 images
wan2.2-t2i-plus `Recommended`	Wan 2.2 Professional Edition. Fully upgraded in creativity, stability, and realistic texture.	$0.05/image	100 images
wan2.2-t2i-flash `Recommended`	Wan 2.2 Flash Edition. Fully upgraded in creativity, stability, and realistic texture.	$0.025/image	100 images
wan2.1-t2i-plus	Wan 2.1 Professional Edition. Supports multiple styles and generates images with rich details.	$0.05/image	200 images
wan2.1-t2i-turbo	Wan 2.1 Turbo Edition. Supports multiple styles and offers fast generation speed.	$0.025/image	200 images

Mainland China (Beijing)

Model	Description	Unit price	Free quota(Note) _{Validity period: Within 90 days after you activate Alibaba Cloud Model Studio.}
wan2.5-t2i-preview `Recommended`	Wan 2.5 preview. The single-side length limit is removed. You can freely select dimensions within the total pixel area and aspect ratio constraints.	$0.028671/image	No free quota
wan2.2-t2i-plus `Recommended`	Wan 2.2 Professional Edition. Fully upgraded in creativity, stability, and realistic texture.	$0.02007/image	No free quota
wan2.2-t2i-flash `Recommended`	Wan 2.2 Flash Edition. Fully upgraded in creativity, stability, and realistic texture.	$0.028671/image	No free quota
wanx2.1-t2i-plus	Wan 2.1 Professional Edition. Supports multiple styles and generates images with rich details.	$0.028671/image	No free quota
wanx2.1-t2i-turbo	Wan 2.1 Turbo Edition. Supports multiple styles and offers fast generation speed.	$0.020070/image	No free quota
wanx2.0-t2i-turbo	Wan 2.0 Turbo Edition. Excels at textured portraits and creative designs. It is cost-effective.	$0.005735/image	No free quota

Input prompt	Output image
A needle-felted Santa Claus holding a gift and a white cat standing next to him against a background of colorful gifts and green plants, creating a cute, warm, and cozy scene.

Wan2.5 general image editing

The Wan2.5 general image editing model supports entity-consistent image editing and multi-image fusion. It accepts text, a single image, or multiple images as input. API reference

International (Singapore)

Model

Unit price

Free quota(Note)

_{Validity period: Within 90 days after you activate Alibaba Cloud Model Studio.}

wan2.5-i2i-preview

$0.03/image

50 images

Mainland China (Beijing)

Model	Unit price	Free quota
wan2.5-i2i-preview	$0.028671/image	No free quota

Feature

Input example

Output image

Single-image editing

damotest2023_Portrait_photography_outdoors_fashionable_beauty_409ae3c1-19e8-4515-8e50-b3c9072e1282_2-转换自-png

Change the floral dress to a vintage-style lace long dress with exquisite embroidery details on the collar and cuffs.

a26b226d-f044-4e95-a41c-d1c0d301c30b-转换自-png

Multi-image fusion

图像编辑2

Place the alarm clock from image 1 next to the vase on the dining table in image 2.

图像编辑2

Wan2.1 general image editing

The Wan2.1 general image editing model performs diverse image editing with simple instructions. It is suitable for scenarios such as outpainting, watermark removal, style transfer, image restoration, and image enhancement. Usage | API reference

Note

This feature is only available in the China (Beijing) region.

Model	Unit price	Free quota
wanx2.1-imageedit	$0.020070 per image	No free quota

The general image editing model currently supports the following features:

Feature	Input image	Input prompt	Output image
Global stylization		Convert to a French picture book style.
Local stylization		Change the house to a wooden plank style.
Instruction-based editing		Change the girl's hair to red.
Inpainting	Input image Masked image (The white area is the mask)	A ceramic rabbit holding a ceramic flower.	Output image
Text watermark removal		Remove the text from the image.
Outpainting		A green fairy.
Image super-resolution	Blurry image	Image super-resolution.	Clear image
Image colorization		Blue background, yellow leaves.
Line art to image		A living room in a minimalist Nordic style.
Placeholder Image		A cartoon character cautiously peeks out, spying on a brilliant blue gem inside the room.

OutfitAnyone

Compared to the basic version, the OutfitAnyone-Plus model offers improvements in image definition, clothing texture details, and logo restoration. However, it takes longer to generate images and is suitable for scenarios that are not time-sensitive. API reference | Try it online
OutfitAnyone-Image Parsing supports parsing model and clothing images, which can be used for pre-processing and post-processing of OutfitAnyone images. API reference

Note

This feature is only available in the China (Beijing) region.

Model	Description	Sample input	Sample output
aitryon-plus	OutfitAnyone-Plus
aitryon-parsing-v1	OutfitAnyone-Image Parsing

OutfitAnyone pricing

Model Service	Model	Unit Price	Discount	Tier
OutfitAnyone-Plus	aitryon-plus	$0.071677/image	None	None
OutfitAnyone-Image Parsing	aitryon-parsing-v1	$0.000574/image	None	None

Video generation - Wan

Text-to-video

The Wan text-to-video model generates videos from a single sentence. The videos feature rich artistic styles and cinematic quality. API reference | Try it online

International (Singapore)

Model	Description	Unit price	Free quota (Claim) _{Valid for 90 days after you activate Alibaba Cloud Model Studio}
wan2.5-t2v-preview `Recommended`	Wan 2.5 preview. Supports automatic voiceover and custom audio file input.	480p: $0.05/second 720p: $0.10/second 1080p: $0.15/second	50 seconds
wan2.2-t2v-plus `Recommended`	Wan 2.2 Professional Edition. Significantly improved image detail and motion stability.	480p: $0.02/second 1080p: $0.10/second	50 seconds
wan2.1-t2v-turbo	Wan 2.1 Turbo Edition. Fast generation speed and balanced performance.	$0.036/second	200 seconds
wan2.1-t2v-plus	Wan 2.1 Professional Edition. Generates rich details and higher-quality images.	$0.10/second	200 seconds

Mainland China (Beijing)

Model	Description	Unit price	Free quota
wan2.5-t2v-preview `Recommended`	Wan 2.5 preview. Supports automatic voiceover and custom audio file input.	480p: $0.043006/second 720p: $0.086012/second 1080p: $0.143353/second	No free quota
wan2.2-t2v-plus `Recommended`	Wan 2.2 Professional Edition. Significantly improved image detail and motion stability.	480p: $0.02007/second 1080p: $0.100347/second	No free quota
wanx2.1-t2v-turbo	Faster generation speed and balanced performance.	$0.034405/second	No free quota
wanx2.1-t2v-plus	Generates richer details and higher-quality images.	$0.100347/second	No free quota

Input example

Output video (wan2.5)

Input prompt: Shot from a low angle, in a medium close-up, with warm tones, mixed lighting (the practical light from the desk lamp blends with the overcast light from the window), side lighting, and a central composition. In a classic detective office, wooden bookshelves are filled with old case files and ashtrays. A green desk lamp illuminates a case file spread out in the center of the desk. A fox, wearing a dark brown trench coat and a light gray fedora, sits in a leather chair, its fur crimson, its tail resting lightly on the edge, its fingers slowly turning yellowed pages. Outside, a steady drizzle falls beneath a blue sky, streaking the glass with meandering streaks. It slowly raises its head, its ears twitching slightly, its amber eyes gazing directly at the camera, its mouth clearly moving as it speaks in a smooth, cynical voice: 'The case was cold, colder than a fish in winter. But every chicken has its secrets, and I, for one, intended to find them '.

Input audio:

Image-to-video - based on the first frame

The Wan image-to-video model uses an input image as the first frame of a video. It then generates the rest of the video based on a prompt. The videos feature rich artistic styles and cinematic quality.API reference | Try it online

International (Singapore)

Model	Description	Unit price	Free quota (Note) _{Validity: Within 90 days after you activate Alibaba Cloud Model Studio}
wan2.5-i2v-preview `Recommended`	Wan 2.5 preview. Supports automatic dubbing and custom audio file uploads.	480P: $0.05/second 720P: $0.10/second 1080P: $0.15/second	50 seconds
wan2.2-i2v-flash `Recommended`	Wan 2.2 Flash Edition. Delivers extremely fast generation speed with significant improvements in visual detail and motion stability.	480P: $0.015/second 720P: $0.036/second	50 seconds
wan2.2-i2v-plus `Recommended`	Wan 2.2 Professional Edition. Delivers significant improvements in visual detail and motion stability.	480P: $0.02/second 1080P: $0.10/second	50 seconds
wan2.1-i2v-turbo	Wan 2.1 Turbo Edition. Fast generation speed with balanced performance.	$0.036/second	200 seconds
wan2.1-i2v-plus	Wan 2.1 Professional Edition. Generates rich details and produces higher-quality, more textured visuals.	$0.10/second	200 seconds

Mainland China (Beijing)

Model	Description	Unit price	Free quota
wan2.5-i2v-preview `Recommended`	Wan 2.5 preview. Supports automatic dubbing and custom audio file uploads.	480P: $0.043006/second 720P: $0.086012/second 1080P: $0.143353/second	No free quota
wan2.2-i2v-plus `Recommended`	Wan 2.2 Professional Edition. Delivers significant improvements in visual detail and motion stability.	480P: $0.02007/second 1080P: $0.100347/second	No free quota
wanx2.1-i2v-turbo	Wan 2.1 Turbo Edition. Fast generation speed with balanced performance.	$0.034405/second	No free quota
wanx2.1-i2v-plus	Wan 2.1 Professional Edition. Generates rich details and produces higher-quality, more textured visuals.	$0.100347/second	No free quota

Input first frame image and audio

Output video (wan2.5)

rap-转换自-png

Input audio:

Input prompt: A scene of urban fantasy art. A dynamic graffiti art character. A boy painted with spray paint comes to life from a concrete wall. He sings an English rap song at a very fast pace while striking a classic, energetic rapper pose. The scene is set under an urban railway bridge at night. The lighting comes from a single streetlight, creating a cinematic atmosphere full of high energy and amazing detail. The audio of the video consists entirely of the boy's rap, with no other dialogue or noise.

Image-to-video - based on the first and last frames

The Wan first-and-last-frame video model generates a smooth, dynamic video from a prompt. You only need to provide the first and last frame images. The videos feature rich artistic styles and cinematic quality. API reference | Try it online

International (Singapore)

Model

Unit price

Free quota (Note)

wan2.1-kf2v-plus

$0.10/second

200 seconds

Validity period: Within 90 days after you activate Model Studio

Mainland China (Beijing)

Model	Unit price	Free quota (Note)
wanx2.1-kf2v-plus	$0.100347/second	No free quota

Example input			Output video
First frame	Last frame	Prompt	Output video
		In a realistic style, the camera starts at eye level with a small black cat looking up at the sky with curiosity, then gradually moves upward, ending in a top-down shot focused on the cat's curious eyes.

General video editing

The Wan unified video editing model supports multimodal inputs, including text, images, and videos. It can perform video generation and general editing tasks. API reference | Try it online

International (Singapore)

Model

Unit price

Free quota (Note)

wan2.1-vace-plus

$0.1/s

50 seconds

Validity: Valid for 90 days after Model Studio activation.

Mainland China (Beijing)

Model	Unit price	Free quota (Note)
wanx2.1-vace-plus	$0.100347/s	No free quota

The unified video editing model supports the following features:

Feature	Input reference image	Input prompt	Output video
Multi-image reference	Reference image 1 (reference entity) Reference image 2 (reference background)	In the video, a girl gracefully walks out from a misty, ancient forest. Her steps are light, and the camera captures her every nimble moment. When the girl stops and looks around at the lush woods, a smile of surprise and joy blossoms on her face. This scene, frozen in a moment of interplay between light and shadow, records the girl's wonderful encounter with nature.	Output video
Video repainting		The video shows a black steampunk-style car driven by a gentleman. The car is decorated with gears and copper pipes. The background features a steam-powered candy factory and retro elements, creating a vintage and playful scene.
Local editing	Input video Input mask image (The white area indicates the editing area)	The video shows a Parisian-style French cafe where a lion in a suit is elegantly sipping coffee. It holds a coffee cup in one hand, taking a gentle sip with a relaxed expression. The cafe is tastefully decorated, with soft hues and warm lighting illuminating the area where the lion is.	The content in the editing area is modified based on the prompt.
Video extension	Input first clip (1 second)	A dog wearing sunglasses is skateboarding on the street, 3D cartoon.	Output extended video (5 seconds)
Video outpainting		An elegant lady is passionately playing the violin, with a full symphony orchestra behind her.

Wan - digital human

This feature generates natural-looking videos of people speaking, singing, or performing, based on a single character image and an audio file. To use this feature, call the following models in sequence. wan2.2-s2v image detection | wan2.2-s2v video generation

Note

This feature is only available in the China (Beijing) region.

Model	Description	Unit price

wan2.2-s2v-detect	Checks whether an input image meets requirements, such as definition, a single person, and a frontal view.	$0.000574/image
wan2.2-s2v	Generates a dynamic video of a person from a valid image and an audio clip.	480P: $0.071677/second 720P: $0.129018/second

Sample input

Output video

p1001125-转换自-jpeg

Input audio:

Wan - animate image

Available in standard and professional modes. The model transfers the actions and expressions from a reference video to a character image, generating a video that animates the character from the image. API reference.

International (Singapore)

Model	Service	Description	Unit price	Free quota (View)
wan2.2-animate-move	Standard mode `wan-std`	Fast generation speed. Meets basic needs such as simple animation demos. Cost-effective.	$0.12/second	The two services share 50 seconds
wan2.2-animate-move	Professional mode `wan-pro`	High animation smoothness. Natural transitions for actions and expressions. The result is similar to a live-action video.	$0.18/second	The two services share 50 seconds

Mainland China (Beijing)

Model	Service	Description	Unit price	Free quota (View)
wan2.2-animate-move	Standard mode `wan-std`	Fast generation speed. Meets basic needs such as simple animation demos. Cost-effective.	$0.06/second	No free quota
wan2.2-animate-move	Professional mode `wan-pro`	High animation smoothness. Natural transitions for actions and expressions. The result is similar to a live-action video.	$0.09/second	No free quota

Character image	Reference video	Output video (standard)	Output video (professional)

Wan - video face swap

Available in standard and professional modes. The model replaces the main character in a video with a character from an image. It preserves the original video's scene, lighting, and hue. API reference.

International (Singapore)

Model	Service	Description	Unit price	Free quota (View)
wan2.2-animate-mix	Standard mode `wan-std`	Generates animations quickly. Ideal for basic requirements, such as simple demos. Highly cost-effective.	$0.18/s	The two services share 50 seconds
wan2.2-animate-mix	Professional mode `wan-pro`	Produces highly smooth animations with natural transitions for actions and expressions. The result closely resembles a live-action video.	$0.26/s	The two services share 50 seconds

Mainland China (Beijing)

Model	Service	Description	Unit price	Free quota (View)
wan2.2-animate-mix	Standard mode `wan-std`	Generates animations quickly. Ideal for basic requirements, such as simple demos. Highly cost-effective.	$0.09/s	No free quota
wan2.2-animate-mix	Professional mode `wan-pro`	Produces highly smooth animations with natural transitions for actions and expressions. The result closely resembles a live-action video.	$0.13/s	No free quota

Character image	Reference video	Output video (standard)	Output video (professional)

AnimateAnyone

This feature generates character motion videos based on a character image and a motion template. To use this feature, call the following three models in sequence. AnimateAnyone image detection API details | AnimateAnyone motion template generation | AnimateAnyone video generation API details

Note

This feature is only available in the China (Beijing) region.

Model	Description	Unit price
animate-anyone-detect-gen2	Detects whether an input image meets the required specifications.	$0.000574/image
animate-anyone-template-gen2	Extracts character motion from a video and generates a motion template.	$0.011469/second
animate-anyone-gen2	Generates a character motion video based on a character image and a motion template.	$0.011469/second

Input: Character image	Input: Motion video	Output (image background)	Output (video background)

Note

The preceding example was generated by the Tongyi App, which integrates AnimateAnyone.
The content generated by the AnimateAnyone model is video only and does not include audio.

EMO

This feature generates dynamic portrait videos based on a portrait image and a human voice audio file. To use this feature, call the following models in sequence. EMO image detection | EMO video generation

Note

This feature is only available in the China (Beijing) region.

Model	Description	Unit price
emo-detect-v1	Detects if an input image meets the required specifications. This model can be called directly without deployment.	$0.000574/image
emo-v1	Generates a dynamic portrait video. This model can be called directly without deployment.	Generating a 1:1 aspect ratio video: $0.011469/second Generating a 3:4 aspect ratio video: $0.022937/second

Input: Portrait image and human voice audio file

Output: Dynamic portrait video

Portrait:

上春山

Human voice audio: See the video on the right.

Character video:

Action style intensity: active ("style_level": "active")

LivePortrait

This is a lightweight model that quickly generates dynamic portrait videos based on a portrait image and a human voice audio file. Compared to the EMO model, it generates videos faster and at a lower cost, but the quality is not as good. To use this feature, call the following two models in sequence. LivePortrait image detection | LivePortrait video generation

Note

This feature is only available in the China (Beijing) region.

Model	Description	Unit price
liveportrait-detect	Detects whether the input image meets the requirements.	$0.000574/image
liveportrait	Generates a dynamic portrait video.	$0.002868/second

Input: Portrait image and voice audio file

Output: Animated portrait video

Portrait image:

Emoji男孩

Voice audio: From the video on the right.

Portrait video:

Emoji

This feature generates dynamic face videos based on a face image and preset facial motion templates. This capability can be used for scenarios such as creating emojis and generating video materials. To use this feature, call the following models in sequence. Emoji image detection | Emoji video generation

Note

This feature is only available in the China (Beijing) region.

Model	Description	Unit price
emoji-detect-v1	Detects whether an input image meets the specified requirements.	$0.000574/image
emoji-v1	Generates a character emoji based on a portrait image and a specified emoji template.	$0.011469/second

Input: Portrait image	Output: Dynamic portrait video
	Template parameter for the "happy" emoji: ("input.driven_id": "mengwa_kaixin")

VideoRetalk

This feature generates a video where the character's lip movements match the input audio, based on a character video and a human voice audio file. To use this feature, call the following model. API reference

Note

This feature is only available in the China (Beijing) region.

Model	Description	Unit price
videoretalk	Generates a new video where the character's lip movements are synchronized with the input audio.	$0.011469/second

Video style transfer

This model supports generating videos in different styles that match the semantic description of user-input text, or restyling a user-input video. API reference

Note

This feature is only available in the China (Beijing) region.

Model	Description	Unit price

video-style-transform	Transforms an input video into styles such as Japanese manga or American comics.	720p	$0.071677/second
		540p	$0.028671/second

Input video	Output video (Japanese manga style)

Speech synthesis (text-to-speech)

Qwen-TTS

Qwen-TTS is a speech synthesis model from the Qwen series. It supports Chinese, English, and mixed Chinese-English text input, and streams audio output. Usage | API reference

International (Singapore)

Model

Version

Unit price

Max input characters

Supported languages

Free quota (Note)

qwen3-tts-flash

Its capabilities are the same as qwen3-tts-flash-2025-09-18

Stable

$0.1/10,000 characters

600

Chinese (Mandarin, Beijing, Shanghai, Sichuan, Nanjing, Shaanxi, Minnan, Tianjin), Cantonese, English, Spanish, Russian, Italian, French, Korean, Japanese, German, Portuguese

2,000 characters for each

Validity: Within 90 days after you activate Model Studio

qwen3-tts-flash-2025-09-18

Snapshot

Qwen3-TTS is billed based on the number of input characters. The billing rules are as follows:

1 Chinese character = 2 characters
1 English letter, 1 punctuation mark, or 1 space = 1 character

Mainland China (Beijing)

Qwen3-TTS

Model

Version

Unit price

Max input characters

Supported languages

qwen3-tts-flash

Its capabilities are the same as qwen3-tts-flash-2025-09-18

Stable

$0.114682/10,000 characters

600

Chinese (Mandarin, Beijing, Shanghai, Sichuan, Nanjing, Shaanxi, Minnan, Tianjin), Cantonese, English, Spanish, Russian, Italian, French, Korean, Japanese, German, Portuguese

qwen3-tts-flash-2025-09-18

Snapshot

Qwen3-TTS is billed based on the number of input characters. The billing rules are as follows:

1 Chinese character = 2 characters
1 English letter, 1 punctuation mark, or 1 space = 1 character

Qwen-TTS

Model	Version	Context window	Max input	Max output	Input cost	Output cost
		(Tokens)			(Thousand tokens)
qwen-tts Its capabilities are the same as qwen-tts-2025-04-10	Stable	8,192	512	7,680	$0.230	$1.434
qwen-tts-latest Its capabilities are always the same as the latest snapshot version	Latest
qwen-tts-2025-05-22	Snapshot
qwen-tts-2025-04-10

Audio is converted to tokens at a rate of 50 tokens per second. Audio shorter than 1 second is counted as 50 tokens.

Qwen-TTS-Realtime

Based on Qwen-TTS, this model supports streaming text input and can adapt its speech rate based on text content and punctuation. It supports Chinese, English, and mixed Chinese-English text input, and streams audio output. Usage

International (Singapore)

Model

Version

Unit price

Supported languages

Free quota (Note)

qwen3-tts-flash-realtime

Current capabilities are equivalent to qwen3-tts-flash-realtime-2025-09-18

Stable

$0.13 per 10,000 characters

Chinese (Mandarin, Beijing, Shanghai, Sichuan, Nanjing, Shaanxi, Minnan, Tianjin), Cantonese, English, Spanish, Russian, Italian, French, Korean, Japanese, German, Portuguese

2,000 characters for each

Validity: Within 90 days after you activate Model Studio

qwen3-tts-flash-realtime-2025-09-18

Snapshot

Qwen3-TTS is billed based on the number of input characters. The billing rules are as follows:

1 Chinese character = 2 characters
1 English letter, 1 punctuation mark, or 1 space = 1 character

Mainland China (Beijing)

Qwen3-TTS Realtime

Model

Version

Unit price

Supported languages

qwen3-tts-flash-realtime

Current capabilities are equivalent to qwen3-tts-flash-realtime-2025-09-18

Stable

$0.143353 per 10,000 characters

Chinese (Mandarin, Beijing, Shanghai, Sichuan, Nanjing, Shaanxi, Minnan, Tianjin), Cantonese, English, Spanish, Russian, Italian, French, Korean, Japanese, German, Portuguese

qwen3-tts-flash-realtime-2025-09-18

Snapshot

Qwen3-TTS is billed based on the number of input characters. The billing rules are as follows:

1 Chinese character = 2 characters
1 English letter, 1 punctuation mark, or 1 space = 1 character

Qwen-TTS Realtime

Model	Version	Context window	Max input	Max output	Input cost	Output cost	Supported languages
		(Tokens)			(Thousand tokens)
qwen-tts-realtime Current capabilities are equivalent to qwen-tts-realtime-2025-07-15	Stable	8,192	512	7,680	$0.345	$1.721	Chinese, English
qwen-tts-realtime-latest Current capabilities are equivalent to qwen-tts-realtime-2025-07-15	Latest						Chinese, English
qwen-tts-realtime-2025-07-15	Snapshot						Chinese, English

Audio-to-token conversion rule: 1 second of audio corresponds to 50 tokens. Audio shorter than 1 second is counted as 50 tokens.

CosyVoice

CosyVoice is a new-generation, large-scale generative speech synthesis model from Qwen Lab. It integrates text understanding and speech generation based on large-scale, pre-trained language models and supports real-time, streaming text-to-speech synthesis. Usage | Try it online | Voice list

Note

This feature is only available in the China (Beijing) region.

Model	Price
cosyvoice-v2	$0.286706 per 10,000 characters

Each Chinese character counts as two characters. Each English letter, punctuation mark, and space counts as one character.

Speech recognition and translation (speech-to-text)

Qwen3-LiveTranslate-Flash-Realtime

qwen3-livetranslate-flash-realtime is a multilingual, real-time audio and video translation model. It recognizes 18 languages and translates them into audio in 10 languages in real time.

Core features:

Multilingual support: Supports 18 languages, such as Chinese, English, French, German, Russian, Japanese, and Korean, and 6 Chinese dialects, such as Mandarin, Cantonese, and Sichuanese.
Visual enhancement: Improves translation accuracy using visual content. The model analyzes lip movements, actions, and on-screen text to improve translation in noisy environments or for words with multiple meanings.
Low latency: Achieves a simultaneous interpretation latency as low as 3 seconds.
Lossless simultaneous interpretation: Uses semantic unit prediction technology to resolve cross-language word order issues. This ensures that the quality of real-time translation is nearly identical to that of offline translation.
Natural voice: Generates human-like speech with a natural voice. The model adapts its tone and emotion based on the source audio content.

Usage

Note

This model is available only in the Singapore region.

Model	Version	Context window	Max input	Max output	Free quota (Note)
		(Tokens)
qwen3-livetranslate-flash-realtime Its capabilities are equivalent to qwen3-livetranslate-flash-realtime-2025-09-22.	Stable	53,248	49,152	4,096	1 million tokens This is valid for 90 days after you activate Model Studio.
qwen3-livetranslate-flash-realtime-2025-09-22	Snapshot

After the free quota is exhausted, inputs and outputs are billed as follows:

Input	Price
Audio	$10
Image	$1.3

Output	Price
Text	$10
Audio	$38

Qwen-ASR

Built on the Qwen multi-modal base model, this model supports features such as multilingual recognition, singing recognition, and noise rejection.Usage

International (Singapore)

Model

Version

Supported languages

Supported sample rates

Unit price

Free quota (Note)

qwen3-asr-flash

Currently an alias for qwen3-asr-flash-2025-09-08

Stable version

Chinese (including Mandarin, Sichuanese, Minnan, Wu, and Cantonese), English, Japanese, German, Korean, Russian, French, Portuguese, Arabic, Italian, and Spanish

16 kHz

$0.000035/second

36,000 seconds (10 hours)

Valid for 90 days after you activate Alibaba Cloud Model Studio

qwen3-asr-flash-2025-09-08

Snapshot version

Mainland China (Beijing)

Model

Version

Supported languages

Supported sample rates

Unit price

qwen3-asr-flash

Alias for qwen3-asr-flash-2025-09-08

Stable version

Chinese (Mandarin, Sichuanese, Minnan, Wu, and Cantonese), English, Japanese, German, Korean, Russian, French, Portuguese, Arabic, Italian, and Spanish

16 kHz

$0.000032/second

qwen3-asr-flash-2025-09-08

Snapshot version

Qwen-ASR-Realtime

The Qwen real-time speech recognition model features automatic language detection. It can detect 11 languages and accurately transcribes audio in complex environments. Usage | API reference

International (Singapore)

Model

Version

Supported languages

Supported sample rates

Unit price

Free quota (Note)

qwen3-asr-flash-realtime

Currently equivalent to qwen3-asr-flash-realtime-2025-10-27

Stable

Chinese (Mandarin, Sichuanese, Minnan, Wu), Cantonese, English, Japanese, German, Korean, Russian, French, Portuguese, Arabic, Italian, Spanish

8 kHz, 16 kHz

$0.000090/second

36,000 seconds (10 hours)

Validity: Within 90 days after you activate Model Studio

qwen3-asr-flash-realtime-2025-10-27

Snapshot

Mainland China (Beijing)

Model

Version

Supported languages

Supported sample rates

Unit price

qwen3-asr-flash-realtime

Currently equivalent to qwen3-asr-flash-realtime-2025-10-27

Stable

Chinese (Mandarin, Sichuanese, Minnan, Wu), Cantonese, English, Japanese, German, Korean, Russian, French, Portuguese, Arabic, Italian, Spanish

8 kHz, 16 kHz

$0.000047/second

qwen3-asr-flash-realtime-2025-10-27

Snapshot

Paraformer

Paraformer is a speech recognition model from Tongyi Lab. It offers two versions: audio file recognition and real-time speech recognition.

Audio file recognition

Usage | API reference

Note

This feature is available only in the Mainland China (Beijing) region.

Model	Supported languages	Supported sample rates	Scenarios	Supported audio formats	Unit price
paraformer-v2	Chinese (Mandarin), Chinese dialects (Cantonese, Wu, Minnan, Northeastern, Gansu, Guizhou, Henan, Hubei, Hunan, Ningxia, Shanxi, Shaanxi, Shandong, Sichuan, Tianjin, Jiangxi, Yunnan, Shanghainese), English, Japanese, Korean, German, French, Russian	Any	ApsaraVideo Live	aac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmv	$0.000012/second
paraformer-8k-v2	Chinese (Mandarin)	8 kHz	Phone calls		$0.000012/second

Real-time speech recognition

Usage | API reference

Note

This feature is available only in the Mainland China (Beijing) region.

Model

Supported languages

Supported sample rates

Scenarios

Supported audio formats

Unit price

paraformer-realtime-v2

Chinese (Mandarin), Chinese dialects (Cantonese, Wu, Minnan, Northeastern, Gansu, Guizhou, Henan, Hubei, Hunan, Ningxia, Shanxi, Shaanxi, Shandong, Sichuan, Tianjin, Jiangxi, Yunnan, Shanghainese), English, Japanese, Korean, German, French, Russian

Supports switching between multiple languages.

Any

ApsaraVideo Live, conferences, and more

pcm, wav, mp3, opus, speex, aac, amr

$0.000035/second

paraformer-realtime-8k-v2

8 kHz

Call centers and more

Fun-ASR

Fun-ASR is a speech recognition model from Tongyi Bailin. It offers two versions: audio file recognition and real-time speech recognition.

Audio file recognition

Usage | API reference

International (Singapore)

Model

Version

Supported languages

Supported sample rates

Scenarios

Supported audio formats

Unit price

Free quota (Note)

fun-asr

Currently equivalent to fun-asr-2025-08-25

Stable

Chinese, English

Any

ApsaraVideo Live, phone calls, conference interpretation, and more

aac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmv

$0.000035/second

36,000 seconds (10 hours)

Validity: 90 days

fun-asr-2025-08-25

Snapshot

Mainland China (Beijing)

Model	Version	Supported languages	Supported sample rates	Scenarios	Supported audio formats	Unit price
fun-asr Currently equivalent to fun-asr-2025-08-25	Stable	Chinese, English	Any	ApsaraVideo Live, phone calls, conference interpretation, and more	aac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmv	$0.000032/second
fun-asr-2025-08-25	Snapshot	Chinese, English
fun-asr-mtl Currently equivalent to fun-asr-mtl-2025-08-25	Stable	Chinese, Cantonese, English, Japanese, Thai, Vietnamese, Indonesian
fun-asr-mtl-2025-08-25	Snapshot

Real-time speech recognition

Usage | API Reference

Note

This feature is available only in the Mainland China (Beijing) region.

Model

Version

Supported languages

Supported sample rates

Scenarios

Supported audio formats

Unit price

fun-asr-realtime

Currently equivalent to fun-asr-realtime-2025-09-15

Stable

Chinese, English

16 kHz

ApsaraVideo Live, conferences, call centers, and more

pcm, wav, mp3, opus, speex, aac, amr

$0.000047/second

fun-asr-realtime-2025-09-15

Snapshot

Text embedding

Text embedding models convert text into numerical representations for tasks such as search, clustering, recommendation, and classification. Billing for these models is based on the number of input tokens. API reference

International (Singapore)

Model

Embedding dimension

Batch size

Maximum tokens per row

Supported languages

Price

(Million input tokens)

Free Quota

Note

text-embedding-v4

This post is part of the Qwen3-Embedding series.

2,048, 1,536, 1,024 (default), 768, 512, 256, 128, or 64

8,192

More than 100 languages, including Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, and Russian, along with various programming languages

$0.07

1,000,000 tokens

Valid for 90 days after you activate Model Studio.

text-embedding-v3

1,024 (default), 768, or 512

8,192

Over 50 languages, such as Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, and Russian

500,000 tokens

Valid for 90 days after you activate Model Studio.

Mainland China (Beijing)

Model

Embedding dimension

Batch size

Maximum tokens per row

Supported languages

Price

(Million input tokens)

Free quota

(Note)

text-embedding-v4

This post is part of the Qwen3-Embedding series.

2,048, 1,536, 1,024 (default), 768, 512, 256, 128, or 64

8,192

Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, Russian, over 100 other major languages, and various programming languages

$0.072

No free quota

Multimodal embedding

The multimodal embedding model converts data such as text, images, and videos into a vector of floating-point numbers. This model enables applications such as video classification, image classification, and image-text retrieval. API reference

International (Singapore)

Model

Data format

Embedding dimension

Unit price (Million input tokens)

Free quota (View)

tongyi-embedding-vision-plus

float(32)

1,152

$0.09

1,000,000 tokens

Valid for 90 days after you activate Model Studio.

tongyi-embedding-vision-flash

float(32)

768

Image/Video: $0.03

Text: $0.09

Mainland China (Beijing)

Model	Data type	Embedding dimensions	Unit price (1,000 input tokens)	Free quota (Note)
multimodal-embedding-v1	float(32)	1,024	Free trial	No token quota limit

Text rerank

This feature is typically used for semantic retrieval. Given a query, it sorts a list of candidate documents in descending order of their semantic relevance. API reference.

Note

This feature is only available in the China (Beijing) region.

Model

Maximum number of documents

Max input tokens per item

Max input tokens

Supported languages

Price (Million input tokens)

gte-rerank-v2

500

4,000

30,000

Over 50 languages, including Chinese, English, Japanese, Korean, Thai, Spanish, French, Portuguese, German, Indonesian, and Arabic

$0.115

Max input tokens per item: Each query or document is limited to 4,000 tokens. Input that exceeds this limit is truncated.
Maximum number of documents: Each request is limited to 500 documents.
Max input tokens: The total number of tokens for all queries and documents in a single request is limited to 30,000.

Domain-specific

Intent recognition

The Qwen intent recognition model can quickly and accurately parse user intents in milliseconds and select the appropriate tools to resolve user issues. API reference | Usage

Note

This feature is only available in the China (Beijing) region.

Model	Context window	Max input	Max output	Input cost	Output cost
Model	(Tokens)			(Million tokens)
tongyi-intent-detect-v3	8,192	8,192	1,024	$0.058	$0.144

Role-playing

Qwen's role-playing model is ideal for scenarios that require human-like conversation, such as virtual social interactions, game NPCs, IP character replication, hardware, toys, and in-vehicle systems. This model offers enhanced capabilities in character fidelity, conversation progression, and empathetic listening compared to other Qwen models. Usage

International (Singapore)

Model	Context window	Max input	Max output	Input cost	Output cost
Model	(Tokens)			(Million tokens)
qwen-plus-character-ja	8,192	7,680	512	$0.5	$1.4

Mainland China (Beijing)

Model	Context window	Max input	Max output	Input cost	Output cost
Model	(Tokens)			(Million tokens)
qwen-plus-character	32,768	32,000	4,096	$0.115	$0.287

Retired models

Retired on August 20, 2025

Qwen2

This is Alibaba Cloud's open-source Qwen2. Usage | API reference | Try it online

Model	Context window	Max input	Max output	Input price	Output price	Alternative models
	(tokens)			(Million tokens)
qwen2-72b-instruct	131,072	128,000	6,144	Free for a limited time		Qwen3, DeepSeek, Kimi, and others
qwen2-57b-a14b-instruct	65,536	63,488
qwen2-7b-instruct	131,072	128,000

Qwen1.5

This is Alibaba Cloud's open-source Qwen1.5. Usage | API reference | Try it online

Model	Context window	Max input	Max output	Input price	Output price	Alternative models
	Tokens			(Million tokens)
qwen1.5-110b-chat	8,000	6,000	2,000	Free for a limited time		Qwen3, DeepSeek, Kimi, and others
qwen1.5-72b-chat
qwen1.5-32b-chat
qwen1.5-14b-chat
qwen1.5-7b-chat