Models and pricing - Alibaba Cloud Model Studio - Alibaba Cloud Documentation Center

Flagship models (Singapore region)

Flagship model	Qwen-Max Ideal for complex tasks, most powerful.	Qwen-Plus Balanced performance, speed, and cost.	Qwen-Flash Ideal for simple tasks, fast and low-cost.	Qwen-Coder Excellent code model, 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)	$1.6	$0.4	$0.05	$0.3
Minimum output price (Million tokens)	$6.4	$1.2	$0.4	$1.5

Model overview

Category	Subcategory	Description
Text generation	General-purpose LLMs	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-Edit: Supports Chinese and English prompts and performs complex image and text editing operations, such as style transfer, text modification, and object editing.
Video generation	Text-to-video	Generates videos from a single sentence, offering rich styles and fine image quality.
	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.
	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 can represent the text, suitable for search, clustering, recommendation, and classification tasks.

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

You can use the stable or latest version for more lenient rate limiting conditions.

Qwen-Max

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

The Qwen-Max model does not support deep thinking.

Qwen3-Max

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
		(Tokens)			(Million tokens)
qwen3-max Currently same capabilties as qwen3-max-2025-09-23	Stable	262,144	258,048	65,536	Tiered pricing, see the description below the table.		1 million tokens Valid for 90 days after activating Alibaba Cloud Model Studio
qwen3-max-2025-09-23	Snapshot
qwen3-max-preview	Preview

Qwen3-Max uses tiered pricing based on the number of input tokens (left-open, right-closed intervals).

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

Qwen-Max

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-max Provides the same capabilities as qwen-max-2025-01-25.	Stable	32,768	30,720	8,192	$1.6 50% discount for batch calls	$6.4 50% discount for batch calls	1 million tokens for input and 1 million for output Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen-max-latest Corresponds to the latest snapshot.	Latest				$1.6	$6.4
qwen-max-2025-01-25 Also known as qwen-max-0125, Qwen2.5-Max	Snapshot

Qwen-Plus

This model provides a balance of capabilities. Its inference performance, cost, and speed fall between Qwen-Max and Qwen-Flash, which makes it ideal for moderately complex tasks. Usage | API reference | Try it online | Deep thinking

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-plus 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 values are 262,144. You can adjust this value using the max_input_tokens parameter.	32,768 Maximum chain-of-thought: 81,920	Tiered pricing, see the description below the table.		1 million tokens Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen-plus-latest 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 Maximum chain-of-thought: 38,912	$0.4	Thinking mode $4 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

The qwen-plus, qwen-plus-latest, qwen-plus-2025-09-11, and qwen-plus-2025-07-28 models use tiered pricing based on the number of input tokens per request (left-open, right-closed intervals).

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

The qwen-plus-2025-09-11, qwen-plus-2025-07-28, qwen-plus-2025-07-14, qwen-plus-2025-04-28, qwen-plus-latest, and qwen-plus models support both thinking and non-thinking modes. You can switch between these modes using the enable_thinking parameter. In addition, the capabilities of these models have been significantly improved:

Reasoning capability: In evaluations for math, code, and logical reasoning, it significantly outperforms QwQ and non-reasoning models of a similar size, which achieves top-tier performance in the industry for its scale.
Human preference alignment: It features greatly enhanced capabilities in creative writing, role assumption, multi-turn conversation, and instruction following. Its general capabilities significantly exceed those of models of a similar size.
Agent capability: It achieves industry-leading performance in both thinking and non-thinking modes and can accurately invoke external tools.

Multilingual capability: It supports over 100 languages and dialects, with significantly improved capabilities in multilingual translation, instruction understanding, and common-sense reasoning.

Supported languages

English

Simplified Chinese

Traditional Chinese

French

Spanish

Arabic is written in the Arabic script and is the official language in many Arab countries.

Russian is written in the Cyrillic script and is the official language of Russia and several other countries.

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

German is written in the Latin script and is the official language of countries such as Germany and Austria.

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

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

Danish is written in the Latin script and is the official language of Denmark.

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

Welsh is written in the Latin script and is an official language of Wales.

Finnish is written in the Latin script and is the official language of Finland.

Icelandic is written in the Latin script and is the official language of Iceland.

Swedish is written in the Latin script and is the official language of Sweden.

Norwegian Nynorsk is written in the Latin script and is one of two official written standards for the Norwegian language.

Norwegian Bokmål is written in the Latin script and is the more common of the two official written standards for the Norwegian language.

Japanese is written in Japanese script and is the official language of Japan.

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

Vietnamese is written in the Latin script and is the official language of Vietnam.

Thai is written in the Thai script and is the official language of Thailand.

Indonesian is written in the Latin script and is the official language of Indonesia.

Malay is written in the Latin script and is a major language in countries such as Malaysia.

Burmese is written in the Burmese script and is the official language of Myanmar.

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

Khmer is written in the Khmer script and is the official language of Cambodia.

Lao is written in the Lao script and is the official language of Laos.

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

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

Urdu is written in the Arabic script. It is an official language of Pakistan and is also widely spoken in India.

Nepali is written in the Devanagari script and is the official language of Nepal.

Hebrew is written in the Hebrew script and is the official language of Israel.

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

Persian is written in the Arabic script and is the official language of countries such as Iran and Tajikistan.

Polish is written in the Latin script and is the official language of Poland.

Ukrainian is written in the Cyrillic script and is the official language of Ukraine.

Czech is written in the Latin script and is the official language of the Czech Republic.

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

Bulgarian is written in the Cyrillic script and is the official language of Bulgaria.

Slovak is written in the Latin script and is the official language of Slovakia.

Hungarian is written in the Latin script and is the official language of Hungary.

Slovenian is written in the Latin script and is the official language of Slovenia.

Latvian is written in the Latin script and is the official language of Latvia.

Estonian is written in the Latin script and is the official language of Estonia.

Lithuanian is written in the Latin script and is the official language of Lithuania.

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

Greek is written in the Greek script and is the official language of Greece and Cyprus.

Croatian is written in the Latin script and is the official language of Croatia.

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

Maltese is written in the Latin script and is the official language of Malta.

Serbian is written in the Cyrillic script and is the official language of Serbia.

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

Georgian is written in the Georgian script and is the official language of Georgia.

Armenian is written in the Armenian script and is the official language of Armenia.

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

Kazakh is written in the Cyrillic script and is the official language of Kazakhstan.

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

Tajik is written in the Cyrillic script and is the official language of Tajikistan.

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

Afrikaans is written in the Latin script and is mainly spoken in South Africa and Namibia.

Cantonese is written in Traditional Chinese characters and is a primary language in Guangdong Province, Hong Kong, and Macao.

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

Limburgish is written in the Latin script and is mainly spoken in the Netherlands, Belgium, and parts of Germany.

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

Galician is written in the Latin script and is mainly spoken in the Galicia region of Spain.

Asturian is written in the Latin script and is mainly spoken in the Asturias region of Spain.

Basque is written in the Latin script. It is mainly spoken in the Basque Country of Spain and France and is an official language of the Basque Autonomous Community in Spain.

Occitan is written in the Latin script and is mainly spoken in the southern regions of France.

Venetian is written in the Latin script and is mainly spoken in the Veneto region of Italy.

Sardinian is written in the Latin script and is mainly spoken on the island of Sardinia in Italy.

Sicilian is written in the Latin script and is mainly spoken on the island of Sicily in Italy.

Friulian is written in the Latin script and is mainly spoken in the Friuli-Venezia Giulia region of Italy.

Lombard is written in the Latin script and is mainly spoken in the Lombardy region of Italy.

Ligurian is written in the Latin script and is mainly spoken in the Liguria region of Italy.

Faroese is written in the Latin script. It is mainly spoken in the Faroe Islands and is one of their official languages.

Tosk Albanian is written in the Latin script and is the southern dialect of Albanian.

Silesian is written in the Latin script and is mainly spoken in Poland.

Bashkir is written in the Cyrillic script and is mainly spoken in the Republic of Bashkortostan, Russia.

Tatar is written in the Cyrillic script and is mainly spoken in the Republic of Tatarstan, Russia.

Mesopotamian Arabic is written in the Arabic script and is mainly spoken in Iraq.

Najdi Arabic is written in the Arabic script and is mainly spoken in the Najd region of Saudi Arabia.

Egyptian Arabic is written in the Arabic script and is mainly spoken in Egypt.

Levantine Arabic is written in the Arabic script and is mainly spoken in Syria and Lebanon.

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

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

Tunisian Arabic is written in the Arabic script and is mainly spoken in Tunisia.

Moroccan Arabic is written in the Arabic script and is mainly spoken in Morocco.

Kabuverdianu is written in the Latin script and is mainly spoken in Cape Verde.

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

Eastern Yiddish is written in the Hebrew script and is mainly spoken in Jewish communities.

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

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

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

Punjabi is written in the Gurmukhi script. It is spoken in the Indian state of Punjab and is one of India's official languages.

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

Gujarati is written in the Gujarati script and is an official language of the Indian state of Gujarat.

Malayalam is written in the Malayalam script and is the official language of the Indian state of Kerala.

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

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

Magahi is written in the Devanagari script and is mainly spoken in the Indian state of Bihar.

Odia is written in the Odia script and is the official language of the Indian state of Odisha.

Awadhi is written in the Devanagari script and is mainly spoken in the Indian state of Uttar Pradesh.

Maithili is written in the Devanagari script. It is spoken in the Indian state of Bihar and the Terai plains of Nepal and is one of India's official languages.

Assamese is written in the Bengali script and is the official language of the Indian state of Assam.

Chhattisgarhi is written in the Devanagari script and is mainly spoken in the Indian state of Chhattisgarh.

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

Minangkabau is written in the Latin script and is mainly spoken on the island of Sumatra in Indonesia.

Balinese is written in the Latin script and is mainly spoken on the island of Bali in Indonesia.

Javanese is written in the Latin script but also commonly in the Javanese script. It is widely spoken on the island of Java in Indonesia.

Banjar is written in the Latin script and is mainly spoken on the island of Kalimantan in Indonesia.

Sundanese is written in the Latin script but traditionally in the Sundanese script. It is mainly spoken in the western part of the island of Java in Indonesia.

Cebuano is written in the Latin script and is mainly spoken in the Cebu region of the Philippines.

Pangasinan is written in the Latin script and is mainly spoken in the Pangasinan province of the Philippines.

Iloko is written in the Latin script and is mainly spoken in the Philippines.

Waray is written in the Latin script and is mainly spoken in the Philippines.

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

Papiamento is written in the Latin script and is mainly spoken in Caribbean regions such as Aruba and Curaçao.

Response format: This version fixes response format issues from previous versions, such as abnormal Markdown, intermediate truncation, and incorrect boxed output.

Qwen-Flash

Qwen-Flash is the fastest and most cost-effective model in the Qwen series and is suitable for simple jobs. It uses flexible tiered pricing. Usage | API reference | Try it online | Thinking mode

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-flash This model has the same capabilities as qwen-flash-2025-07-28. Part of the Qwen3 series. A 50% discount applies to batch calls.	Stable	1,000,000	Thinking mode 995,904 Non-thinking mode 997,952	32,768 Maximum chain-of-thought: 81,920.	Tiered pricing, see the description below this table.		1 million input and 1 million output tokens Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen-flash-2025-07-28 Part of the Qwen3 series.	Snapshot

The qwen-flash and qwen-flash-2025-07-28 models use tiered pricing based on the number of input tokens in each request (left-open, right-closed intervals). The qwen-flash model supports caching and batch calling.

Input token count	Input price (Million tokens)	Output price (Million tokens)
0–256K	$0.05	$0.40
256K–1M	$0.25	$2.00

Qwen-Turbo

Qwen-Turbo is deprecated. We recommend Qwen-Flash instead. Qwen-Flash offers flexible tiered pricing for more cost-effective billing. Usage | API reference | Try it online | Deep thinking

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota Note
		(Tokens)			(Million tokens)
qwen-turbo Provides 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 Maximum chain-of-thought: 38,912	$0.05 Half price for batch calling	Thinking mode: $0.5 Non-thinking mode: $0.2 Half price for batch calling	1 million tokens each Valid for 90 days after you activate Alibaba Cloud Model Studio.
qwen-turbo-latest Provides the same capabilities as the latest snapshot. 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

The latest qwen-turbo-2025-04-28 and qwen-turbo-latest models have thinking and non-thinking mode response capabilities. You can switch between the two modes using the enable_thinking parameter. In addition, the model's capabilities have been significantly improved:

Reasoning capability: In evaluations for math, code, and logical reasoning, it significantly outperforms QwQ and non-reasoning models of a similar size, which reaches the top tier in the industry for its scale.
Human preference alignment: Capabilities in creative writing, role assumption, multi-turn conversation, and instruction following are greatly enhanced. Its general capabilities significantly exceed those of models of a similar size.
Agent capability: This model reaches industry-leading levels in both reasoning and non-reasoning modes. It can achieve precise external tool invocation.

Multilingual capability: This model supports over 100 languages and dialects. Capabilities in multilingual translation, instruction understanding, and common-sense reasoning are significantly improved.

Supported languages

English

Simplified Chinese

Traditional Chinese

French

Spanish

Arabic, written in the Arabic script, is the official language of many Arab countries.

Russian, written in the Cyrillic script, is the official language of Russia and some other countries.

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

German, written in the Latin script, is the official language of countries such as Germany and Austria.

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

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

Danish, written in the Latin script, is the official language of Denmark.

Irish, written in the Latin script, is one of the official languages of Ireland.

Welsh, written in the Latin script, is one of the official languages of Wales.

Finnish, written in the Latin script, is the official language of Finland.

Icelandic, written in the Latin script, is the official language of Iceland.

Swedish, written in the Latin script, is the official language of Sweden.

Norwegian Nynorsk, written in the Latin script, is an official written standard for the Norwegian language, used alongside Norwegian Bokmål.

Norwegian Bokmål, written in the Latin script, is the most common written standard for the Norwegian language.

Japanese, written in the Japanese script, is the official language of Japan.

Korean, written in the Hangul script, is the official language of South Korea and North Korea.

Vietnamese, written in the Latin script, is the official language of Vietnam.

Thai, written in the Thai script, is the official language of Thailand.

Indonesian, written in the Latin script, is the official language of Indonesia.

Malay, written in the Latin script, is a major language in countries such as Malaysia.

Burmese, written in the Burmese script, is the official language of Myanmar.

Tagalog, written in the Latin script, is one of the major languages of the Philippines.

Khmer, written in the Khmer script, is the official language of Cambodia.

Lao, written in the Lao script, is the official language of Laos.

Hindi, written in the Devanagari script, is one of the official languages of India.

Bengali, written in the Bengali script, is the official language of Bangladesh and the Indian state of West Bengal.

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

Nepali, written in the Devanagari script, is the official language of Nepal.

Hebrew, written in the Hebrew script, is the official language of Israel.

Turkish, written in the Latin script, is the official language of Türkiye and Northern Cyprus.

Persian, written in the Arabic script, is the official language of countries such as Iran and Tajikistan.

Polish, written in the Latin script, is the official language of Poland.

Ukrainian, written in the Cyrillic script, is the official language of Ukraine.

Czech, written in the Latin script, is the official language of the Czech Republic.

Romanian, written in the Latin script, is the official language of Romania and Moldova.

Bulgarian, written in the Cyrillic script, is the official language of Bulgaria.

Slovak, written in the Latin script, is the official language of Slovakia.

Hungarian, written in the Latin script, is the official language of Hungary.

Slovenian, written in the Latin script, is the official language of Slovenia.

Latvian, written in the Latin script, is the official language of Latvia.

Estonian, written in the Latin script, is the official language of Estonia.

Lithuanian, written in the Latin script, is the official language of Lithuania.

Belarusian, written in the Cyrillic script, is one of the official languages of Belarus.

Greek, written in the Greek script, is the official language of Greece and Cyprus.

Croatian, written in the Latin script, is the official language of Croatia.

Macedonian, written in the Cyrillic script, is the official language of North Macedonia.

Maltese, written in the Latin script, is the official language of Malta.

Serbian, written in the Cyrillic script, is the official language of Serbia.

Bosnian, written in the Latin script, is one of the official languages of Bosnia and Herzegovina.

Georgian, written in the Georgian script, is the official language of Georgia.

Armenian, written in the Armenian script, is the official language of Armenia.

North Azerbaijani, written in the Latin script, is the official language of Azerbaijan.

Kazakh, written in the Cyrillic script, is the official language of Kazakhstan.

Northern Uzbek, written in the Latin script, is the official language of Uzbekistan.

Tajik, written in the Cyrillic script, is the official language of Tajikistan.

Swahili, written in the Latin script, is a lingua franca or official language in many East African countries.

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

Cantonese is written in Traditional Chinese characters and is a major language spoken in Guangdong Province, Hong Kong, and Macao.

Luxembourgish, written in the Latin script, is one of the official languages of Luxembourg and is also spoken in parts of Germany.

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

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

Galician, written in the Latin script, is primarily spoken in the Galicia region of Spain.

Asturian, written in the Latin script, is primarily spoken in the Asturias region of Spain.

Basque, written in the Latin script, is primarily spoken in the Basque Country of Spain and France. It is one of the official languages of the Basque Autonomous Community in Spain.

Occitan, written in the Latin script, is primarily spoken in the southern regions of France.

Venetian, written in the Latin script, is primarily spoken in the Veneto region of Italy.

Sardinian, written in the Latin script, is primarily spoken on the island of Sardinia in Italy.

Sicilian, written in the Latin script, is primarily spoken on the island of Sicily in Italy.

Friulian, written in the Latin script, is primarily spoken in the Friuli-Venezia Giulia region of Italy.

Lombard, written in the Latin script, is primarily spoken in the Lombardy region of Italy.

Ligurian, written in the Latin script, is primarily spoken in the Liguria region of Italy.

Faroese, written in the Latin script, is one of the official languages of the Faroe Islands.

Tosk Albanian, written in the Latin script, is the southern dialect of the Albanian language.

Silesian, written in the Latin script, is primarily spoken in Poland.

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

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

Mesopotamian Arabic, written in the Arabic script, is primarily spoken in Iraq.

Najdi Arabic, written in the Arabic script, is primarily spoken in the Najd region of Saudi Arabia.

Egyptian Arabic, written in the Arabic script, is primarily spoken in Egypt.

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

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

Dari, written in the Arabic script, is one of the official languages of Afghanistan.

Tunisian Arabic, written in the Arabic script, is primarily spoken in Tunisia.

Moroccan Arabic, written in the Arabic script, is primarily spoken in Morocco.

Kabuverdianu, written in the Latin script, is primarily spoken in Cape Verde.

Tok Pisin, written in the Latin script, is a major lingua franca of Papua New Guinea.

Eastern Yiddish, written in the Hebrew script, is primarily spoken in Jewish communities.

Sindhi, written in the Arabic script, is one of the official languages of the Sindh province in Pakistan.

Sinhala, written in the Sinhala script, is one of the official languages of Sri Lanka.

Telugu, written in the Telugu script, is one of the official languages of the Indian states of Andhra Pradesh and Telangana.

Punjabi, written in the Gurmukhi script, is one of India's official languages and is spoken in the state of Punjab.

Tamil, written in the Tamil script, is an official language of the Indian state of Tamil Nadu and of Sri Lanka.

Gujarati, written in the Gujarati script, is one of the official languages of the Indian state of Gujarat.

Malayalam, written in the Malayalam script, is one of the official languages of the Indian state of Kerala.

Marathi, written in the Devanagari script, is one of the official languages of the Indian state of Maharashtra.

Kannada, written in the Kannada script, is one of the official languages of the Indian state of Karnataka.

Magahi, written in the Devanagari script, is primarily spoken in the Indian state of Bihar.

Oriya, written in the Odia script, is one of the official languages of the Indian state of Odisha.

Awadhi, written in the Devanagari script, is primarily spoken in the Indian state of Uttar Pradesh.

Maithili, written in the Devanagari script, is one of India's official languages and is spoken in the Indian state of Bihar and the Terai plains of Nepal.

Assamese, written in the Bengali script, is one of the official languages of the Indian state of Assam.

Chhattisgarhi, written in the Devanagari script, is primarily spoken in the Indian state of Chhattisgarh.

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

Minangkabau, written in the Latin script, is primarily spoken on the island of Sumatra in Indonesia.

Balinese, written in the Latin script, is primarily spoken on the island of Bali in Indonesia.

Javanese, written in the Latin script, is widely spoken on the island of Java in Indonesia. The Javanese script is also commonly used.

Banjar, written in the Latin script, is primarily spoken on the island of Kalimantan in Indonesia.

Sundanese, written in the Latin script, is primarily spoken in the western part of Java, Indonesia. The Sundanese script was also traditionally used.

Cebuano, written in the Latin script, is primarily spoken in the Cebu region of the Philippines.

Pangasinan, written in the Latin script, is primarily spoken in the Pangasinan province of the Philippines.

Iloko, written in the Latin script, is primarily spoken in the Philippines.

Waray (Philippines), written in the Latin script, is primarily spoken in the Philippines.

Haitian Creole, written in the Latin script, is one of the official languages of Haiti.

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

Response format fixes: Fixes response format issues from previous versions, such as abnormal Markdown, intermediate truncation, and incorrect boxed output.

QwQ

QwQ is a reasoning model trained based on the Qwen2.5 model. Its reasoning capability has been significantly improved through reinforcement learning. The model's 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. Usage

Model

Version

Context window

Maximum input

Maximum chain-of-thought

Maximum response

Input price

Output price

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: 90 days after you activate Model Studio

Qwen-Omni

Qwen-Omni accepts multimodal inputs, such as text, images, audio, and video. It generates text or speech responses. The model provides a variety of expressive, human-like voices and supports speech output in multiple languages and dialects. It can be used in audio and video chat scenarios, such as visual recognition, emotion detection, education, and training. Usage | API reference

Qwen3-Omni-Flash

Model	Version	Mode	Context window	Maximum input	Maximum CoT	Maximum output	Free quota (Note)
			(Tokens)
qwen3-omni-flash Currently same capability as qwen3-omni-flash-2025-09-15	Stable	Thinking	65,536	16,384	32,768	16,384	1 million tokens each (regardless of modality) Valid for 90 days after activation
		Non-thinking		49,152	-
qwen3-omni-flash-2025-09-15 Also qwen3-omni-flash-0915	Snapshot	Thinking	65,536	16,384	32,768	16,384
		Non-thinking		49,152	-

After you use up your free quota, inputs and outputs are billed as follows. The billing is the same for both thinking and non-thinking modes. Audio output is not supported in thinking mode.

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

Output billing items

Unit price (Million tokens)

Output: Text

$1.66 (when the input contains only text)

$3.96 (when the input contains images or audio)

Output: Text and audio

This item is not billed in thinking mode.

$15.11 (audio)

The output text is not billed.

Qwen-Omni-Turbo (based on Qwen2.5)

Model	Version	Context window	Maximum input	Maximum output	Free quota (Note)
		(Tokens)
qwen-omni-turbo Currently has the same capabilities as qwen-omni-turbo-2025-03-26.	Stable	32,768	30,720	2,048	1 million tokens each (regardless of modality) This quota is valid for 90 days after you activate Model Studio.
qwen-omni-turbo-latest Always has the same capabilities as the latest snapshot version.	Latest
qwen-omni-turbo-2025-03-26 Also known as qwen-omni-turbo-0326.	Snapshot

After you use up the free quota for the commercial model, the billing rules for inputs and outputs are as follows:

Input billing item	Price (Million tokens)
Input: Text	$0.07
Input: Audio	$4.44
Input: Image/Video	$0.21

Output billing item

Price (Million tokens)

Output: Text

$0.27 (for text-only input)

$0.63 (for input containing images, audio, or video)

Output: Text + Audio

$8.89 (Audio)

The output text is not billed.

Qwen3-Omni-Flash is recommended. It offers significant improvements in capabilities compared to Qwen-Omni-Turbo, which is no longer updated:

It is a hybrid model that supports both thinking and non-thinking modes. You can switch between the two modes using the enable_thinking parameter. The thinking mode is disabled by default.
Audio output is not supported in thinking mode. In non-thinking mode, the model's audio output has the following features:
- The number of supported voices is increased to 17. Qwen-Omni-Turbo supports only 4.
- The number of supported languages is increased to 10. Qwen-Omni-Turbo supports only 2.

Qwen-Omni-Realtime

Unlike Qwen-Omni, Qwen-Omni-Realtime supports audio stream inputs. It has a built-in Voice Activity Detection (VAD) feature that automatically detects the start and end of user speech. Usage｜Client events｜Sever events

Qwen3-Omni-Flash-Realtime

Model	Version	Context window	Maximum input	Maximum output	Free quota (Note)
		(Tokens)
qwen3-omni-flash-realtime Current capabilities are 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 you use up the free quota, the billing rules for inputs and outputs are as follows:

Input billing item	Price (Million tokens)
Input: Text	$0.52
Input: Audio	$4.57
Input: Image/Video	$0.94

Output billing item

Price (Million tokens)

Output: Text

$1.99 (for text-only input)

$3.67 (for input containing images or audio)

Output: Text + Audio

$18.13 (for audio)

The output text is not billed.

Qwen-Omni-Turbo-Realtime (based on Qwen2.5)

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

After you use up the free quota, the billing rules for inputs and outputs are as follows:

Input billing item	Price (Million tokens)
Input: Text	$0.270
Input: Audio	$4.440
Input: Image	$0.840

Output billing item

Price (Million tokens)

Output: Text

$1.070 (for text-only input)

$2.520 (for input containing images or audio)

Output: Text + Audio

$8.890 (for audio)

The output text is not billed.

Qwen3-Omni-Flash-Realtime is recommended. It provides significant improvements over Qwen-Omni-Turbo-Realtime, which will no longer be updated. For audio output from the model:

Supports 17 voices, whereas Qwen-Omni-Turbo-Realtime supports only 4.
Supports 10 languages, whereas Qwen-Omni-Turbo-Realtime supports only 2.

QVQ

QVQ is a visual reasoning model that supports visual input and chain-of-thought output. It demonstrates enhanced capabilities in math, programming, visual analysis, creation, and general tasks. Usage

Model	Version	Context window	Maximum input	Maximum CoT	Maximum response	Input price	Output price	Free quota (Note)
		(Tokens)				(Million tokens)
qvq-max Currently same performance as qvq-max-2025-03-25	Stable	131,072	106,496 Up to 16,384 per image	16,384	8,192	$1.2	$4.8	1 million tokens each Valid for 180 days after activation
qvq-max-latest Always same performance as the latest snapshot	Latest
qvq-max-2025-03-25 Also qvq-max-0325	Snapshot

Qwen-VL

Qwen-VL is a text generation model with visual (image) understanding capabilities. It comes in two series: QwenVL-Max and QwenVL-Plus. It can perform OCR and also summarize and reason. For example, it can extract properties from product photos or solve problems based on exercise diagrams. Usage | API reference | Try it online

Qwen-VL models are billed based on the total number of input and output tokens.

Image token calculation rule: Visual understanding.

Qwen3-VL-Plus

Model	Version	Mode	Context window	Maximum input	Maximum chain-of-thought	Maximum output	Input price	Output price Chain-of-thought + output	Free quota (Note)
			(Tokens)				(Per 1,000 tokens)
qwen3-vl-plus Currently has the same capabilities as qwen3-vl-plus-2025-09-23	Stable	Thinking	262,144	258,048 Max 16,384 per image	81,920	32,768	Tiered pricing. For more information, see the notes below the table.		1 million tokens for input and output each Validity: 90 days after you activate Alibaba Cloud Model Studio
		Non-thinking	262,144	260,096 Max 16,384 per image	-
qwen3-vl-plus-2025-09-23	Snapshot	Thinking	262,144	258,048 Max 16,384 per image	81,920	32,768
		Non-thinking	262,144	260,096 Max 16,384 per image	-

The qwen3-vl-plus and qwen3-vl-plus-2025-09-23 models use a tiered billing method based on the number of input tokens in each request. The input and output prices are the same for both the thinking and non-thinking modes.

Number of input tokens	Input price (Million tokens)	Output price (Million tokens)
0 to 32K	$0.2	$1.6
32K to 128K	$0.3	$2.4
128K to 256K	$0.6	$4.8

QwenVL-Max

This is the most powerful model in the Qwen-VL series. The following models belong to the Qwen2.5-VL series.

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-vl-max Offers further improvements in visual reasoning and instruction following capabilities compared to qwen-vl-plus, delivering optimal performance on more complex tasks. Currently has the same capabilities as qwen-vl-max-2025-08-13	Stable	131,072	129,024 Max 16,384 per image	8,192	$0.8 50% off for batch calls	$3.2 50% off for batch calls	1 million tokens for input and output each Validity: 90 days after you activate Alibaba Cloud Model Studio
qwen-vl-max-latest Always has the same capabilities as the latest snapshot	Latest				$0.8	$3.2
qwen-vl-max-2025-08-13 Also known as qwen-vl-max-0813 Features comprehensive improvements in visual understanding metrics, with significantly enhanced capabilities in mathematics, reasoning, object detection, and multilingual processing.	Snapshot
qwen-vl-max-2025-04-08 Also known as qwen-vl-max-0408 Belongs to the Qwen2.5-VL series. The context is extended to 128k, and the mathematics and reasoning capabilities are significantly enhanced.

QwenVL-Plus

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

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
		(Tokens)			(Million tokens)
qwen-vl-plus Currently has the same capabilities as qwen-vl-plus-2025-08-15	Stable	131,072	129,024 Max 16,384 per image	8,192	$0.21 50% off for batch calls	$0.63 50% off for batch calls	1 million tokens for input and output each Validity: 90 days after you activate Alibaba Cloud Model Studio
qwen-vl-plus-latest Always has the same capabilities as the latest snapshot	Latest				$0.21	$0.63
qwen-vl-plus-2025-08-15 Also known as qwen-vl-plus-0815 Significantly improved capabilities in object detection and localization, and multilingual processing	Snapshot
qwen-vl-plus-2025-05-07 Also known as qwen-vl-plus-0507 Significantly improves the ability to understand mathematics, reasoning, and content from monitoring videos
qwen-vl-plus-2025-01-25 Also known as qwen-vl-plus-0125 Belongs to the Qwen2.5-VL series. The context is extended to 128k, and the image and video understanding capabilities are significantly enhanced.

Qwen-OCR

The Qwen-OCR model is specialized for text extraction. Compared to the Qwen-VL model, it focuses more on extracting text from images such as documents, forms, exam questions, and handwritten text. It can recognize multiple languages, including English, French, Japanese, Korean, German, Russian, and Italian. Usage | API reference | Try it online

Model

Version

Context window

Maximum input

Maximum output

Input and output unit price

Free quota

(Note)

(Tokens)

(Million tokens)

qwen-vl-ocr

Stable

34,096

30,000

A maximum of 30,000 tokens per image.

4,096

$0.72

1 million input tokens and 1 million output tokens

Valid for 90 days after you activate Alibaba Cloud Model Studio.

Qwen-ASR

Based on Qwen's multimodal model, Qwen-ASR supports multilingual recognition, singing recognition, and noise rejection. Usage

Model

Version

Supported languages

Supported sample rates

Unit price

Free quota (Note)

qwen3-asr-flash

Currently equivalent to qwen3-asr-flash-2025-09-08

Stable

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

16 kHz

$0.000035/second

36,000 seconds (10 hours)

Validity: 90 days after you activate Model Studio

qwen3-asr-flash-2025-09-08

Snapshot

Qwen-Coder

This is the Qwen code model. The latest Qwen3-Coder series models are code generation models based on Qwen3. They have powerful coding Agent capabilities, excel at tool calling and environment interaction, and can perform autonomous programming. They combine excellent coding skills with general-purpose capabilities. Usage | API reference

Model	Version	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
		(Tokens)			(Million tokens)
qwen3-coder-plus Currently has the same capabilities as qwen3-coder-plus-2025-07-22	Stable	1,000,000	997,952	65,536	Tiered pricing. See the description below the table.		1 million tokens each Valid for 90 days after you activate Model Studio
qwen3-coder-plus-2025-09-23	Snapshot
qwen3-coder-plus-2025-07-22	Snapshot
qwen3-coder-flash Currently has the same capabilities as qwen3-coder-flash-2025-07-28	Stable
qwen3-coder-flash-2025-07-28	Snapshot

The preceding models use a tiered billing method based on the number of input tokens in each request (left-open, right-closed intervals).

qwen3-coder-plus

The prices for qwen3-coder-plus, qwen3-coder-plus-2025-09-23, and qwen3-coder-plus-2025-07-22 are as follows. qwen3-coder-plus 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	Input cost (Million tokens)	Output cost (Million tokens)
0–32K	$1	$5
32K–128K	$1.8	$9
128K–256K	$3	$15
256K–1M	$6	$60

qwen3-coder-flash series

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

Input tokens	Input cost (Million tokens)	Output cost (Million tokens)
0–32K	$0.3	$1.5
32K–128K	$0.5	$2.5
128K–256K	$0.8	$4
256K–1M	$1.6	$9.6

Qwen-MT

This is a flagship large translation model fully upgraded based on Qwen 3. It supports mutual translation across 92 languages, including Chinese, English, Japanese, Korean, French, Spanish, German, Thai, Indonesian, Vietnamese, and Arabic. The model's performance and translation quality are comprehensively upgraded. It provides more stable term customization, format retention, and domain-specific prompt capabilities, which makes translations more accurate and natural. Usage

Model	Context window	Maximum input	Maximum output	Input price	Output price	Free quota (Note)
	(Tokens)			(Million tokens)
qwen-mt-plus Qwen3-MT	16,384	8,192	8,192	$2.46	$7.37	1 million tokens per model Valid for 90 days after activating Alibaba Cloud Model Studio
qwen-mt-turbo Qwen3-MT				$0.16	$0.49

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 calling 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

The qwen3-next-80b-a3b-thinking model, released in September 2025, supports only thinking mode. It features improved instruction-following capabilities compared to the qwen3-235b-a22b-thinking-2507 model, resulting in more concise summary responses.

The qwen3-next-80b-a3b-instruct model, released in September 2025, supports only non-thinking mode. It offers enhanced Chinese understanding, 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 and supporting only the thinking mode, are upgrades to the thinking mode of the qwen3-235b-a22b and qwen3-30b-a3b models.

The qwen3-235b-a22b-instruct-2507 and qwen3-30b-a3b-instruct-2507 models, released in July 2025 and supporting only the non-thinking mode, are upgrades to the non-thinking mode of the qwen3-235b-a22b and qwen3-30b-a3b models.

The Qwen3 models released in April 2025 support thinking and non-thinking modes. You can switch between the two modes using the enable_thinking parameter. In addition, the capabilities of the Qwen3 models have been significantly improved:

Reasoning capability: In evaluations for math, code, and logical reasoning, it significantly outperforms QwQ and non-reasoning models of a similar size, which reaches the top tier in the industry for its scale.
Human preference alignment: Capabilities in creative writing, role assumption, multi-turn conversation, and instruction following are greatly enhanced. Its general capabilities significantly exceed those of models of a similar size.
Agent capability: This model reaches industry-leading levels in both reasoning and non-reasoning modes. It can achieve precise external tool invocation.