:Qwen LLMs

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

The Qwen-Max model does not currently support deep thinking.

The latest qwen3-max model is an upgrade to the qwen3-max-preview version and is specifically enhanced for agent programming and tool calling. This official release achieves state-of-the-art (SOTA) performance in its domain and is designed for more complex agent requirements.

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

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

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

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

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

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

The Qwen3-Omni-Flash model offers significant improvements over Qwen-Omni-Turbo, which is no longer updated: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

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

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

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.

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

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

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

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

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.

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

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

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:

1. 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.

2. 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.

3. Agent capabilities: The models deliver industry-leading performance in both thinking and non-thinking modes and can perform precise external tool calling.

4. 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.

5. 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

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.