Models
One name per model, however many providers serve it.
Qwen: Qwen3 TTS 1.7B
Accepts- Text
Creates- Audio
Qwen3 TTS is a multilingual text-to-speech model from Alibaba's Qwen team.
qwen/qwen3-tts-1.7bNov 20, 20264K context9 voicesMP3 · WAV7,208 Toman per 1,000 charactersQwen: Qwen4 Max
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen4 Max is the flagship model in Alibaba's Qwen4 series.
qwen/qwen4-maxNov 16, 20261M context515,816 Toman/M input tokens1,544,032 Toman/M output tokensQwen: Qwen Image 2.1 Turbo
Accepts- Text
- Image
Creates- Image
Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak…
qwen/qwen-image-2.1-turboOct 16, 202666K contextUp to 6 images a requestEdits pictures6,631 Toman an imageQwen: Qwen Image 2.1 Pro
Accepts- Text
- Image
Creates- Image
Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series.
qwen/qwen-image-2.1-proOct 16, 202666K contextUp to 6 images a requestEdits pictures16,578 Toman an imageQwen: Qwen3.8 Max Prime
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point.
qwen/qwen3.8-max-primeSep 23, 20261M context1,441,552 Toman/M input tokens4,324,656 Toman/M output tokensQwen: Qwen3.8 Omni Flash
Accepts- Text
- Image
- Audio
- Video
Creates- Text
ToolsJSONReasoningQwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding.
qwen/qwen3.8-omni-flashSep 21, 20261M context54,656 Toman/M input tokens170,800 Toman/M output tokensQwen: Qwen3.8 Max (0902)
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.
qwen/qwen3.8-max-0902Sep 3, 20261M context720,776 Toman/M input tokens2,162,328 Toman/M output tokensQwen: Qwen3.8 Flash
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.
qwen/qwen3.8-flashAug 26, 20261M context54,656 Toman/M input tokens170,800 Toman/M output tokensQwen: Qwen3 Reranker 0.6B
Accepts- Text
CreatesQwen3 Reranker 0.6B is the smallest text reranking model from Alibaba Cloud in the Qwen3 Reranker series.
qwen/qwen3-reranker-0.6bAug 26, 202633K contextThe provider's cost of each request, plus your plan's marginQwen: Qwen3.8 27B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.8 27B is an open-weight dense vision-language model from Qwen.
qwen/qwen3.8-27bAug 14, 20261M context13,664 Toman/M input tokens543,144 Toman/M output tokensQwen: Qwen3 Reranker 8B
Accepts- Text
CreatesQwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture.
qwen/qwen3-reranker-8bAug 13, 202641K contextThe provider's cost of each request, plus your plan's marginQwen: Qwen3 ASR 1.7B
Accepts- Audio
Creates- Text
Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen.
qwen/qwen3-asr-1.7bAug 13, 2026With segment and word times162 Toman a minute of audioQwen: Qwen3 ASR 0.6B
Accepts- Audio
Creates- Text
Qwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen.
qwen/qwen3-asr-0.6bAug 13, 2026With segment and word times72 Toman a minute of audioQwen: Qwen3.8 2.4T A95B
Accepts- Text
Creates- Text
ToolsJSONReasoningQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total.
qwen/qwen3.8-2.4t-a95bAug 12, 20261M context720,776 Toman/M input tokens2,162,328 Toman/M output tokensQwen: Qwen Image 3
Accepts- Text
- Image
Creates- Image
Qwen Image 3 is a unified image generation and editing model from Qwen.
qwen/qwen-image-3Aug 5, 202666K contextUp to 6 images a requestEdits pictures10,812 Toman an imageQwen: Qwen Image 3 Pro
Accepts- Text
- Image
Creates- Image
Qwen Image 3 Pro is an image generation and editing model from Qwen.
qwen/qwen-image-3-proAug 5, 202666K contextUp to 6 images a requestEdits pictures14,416 Toman to 27,029 Toman an imageQwen: Qwen3.7 Flash
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.7 Flash is a vision-language reasoning model from Alibaba.
qwen/qwen3.7-flashJul 27, 20261M context13,664 Toman/M input tokens47,824 Toman/M output tokensdearer above 32K tokensQwen: Qwen-Audio-3.0-TTS Flash
Accepts- Text
Creates- Audio
Qwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.
qwen/qwen-audio-3.0-tts-flashJul 23, 20262 voicesMP3 · WAV5,406 Toman per 1,000 charactersQwen: Qwen-Audio-3.0-TTS Plus
Accepts- Text
Creates- Audio
Qwen-Audio-3.0-TTS Plus is Alibaba's higher-quality text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesizer API.
qwen/qwen-audio-3.0-tts-plusJul 23, 20262 voicesMP3 · WAV7,208 Toman per 1,000 charactersQwen: Qwen3.7 Plus
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningQwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.
qwen/qwen3.7-plusJun 3, 20261M context116,144 Toman/M input tokens464,576 Toman/M output tokensdearer above 256K tokensQwen: Qwen3.7 Max
Accepts- Text
Creates- Text
ToolsJSONReasoningQwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.
qwen/qwen3.7-maxMay 21, 20261M context532,896 Toman/M input tokens1,595,272 Toman/M output tokensQwen: Qwen3.5 Plus 2026-04-20
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window.
qwen/qwen3.5-plus-20260420Apr 27, 20261M context109,312 Toman/M input tokens649,040 Toman/M output tokensdearer above 256K tokensQwen: Qwen3.6 Flash
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window.
qwen/qwen3.6-flashApr 27, 20261M context68,320 Toman/M input tokens406,504 Toman/M output tokensdearer above 256K tokensQwen: Qwen3.6 35B A3B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.
qwen/qwen3.6-35b-a3bApr 27, 2026262K context37,576 Toman/M input tokens324,520 Toman/M output tokensQwen: Qwen3.6 27B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
qwen/qwen3.6-27bApr 27, 2026262K context116,144 Toman/M input tokens1,154,608 Toman/M output tokensQwen: Qwen3.6 Plus
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference.
qwen/qwen3.6-plusApr 2, 20261M context119,560 Toman/M input tokens703,696 Toman/M output tokensdearer above 256K tokensQwen: Qwen3.5-9B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.
qwen/qwen3.5-9bMar 10, 2026262K context61,488 Toman/M input tokens92,232 Toman/M output tokensQwen: Qwen3.5-35B-A3B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningThe Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.
qwen/qwen3.5-35b-a3bFeb 25, 2026262K context51,240 Toman/M input tokens362,096 Toman/M output tokensQwen: Qwen3.5-27B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningThe Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance.
qwen/qwen3.5-27bFeb 25, 2026262K context95,648 Toman/M input tokens939,400 Toman/M output tokensQwen: Qwen3.5-122B-A10B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningThe Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.
qwen/qwen3.5-122b-a10bFeb 25, 2026262K context95,648 Toman/M input tokens751,520 Toman/M output tokens
54 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

