Catalogue
Models
376 models, cross-linked to hardware verdicts and live provider pricing.
44 models
Qwen3.73 sizes here
Qwen3.7 FlashQwenQwen3.7 Flash is a hosted-only multimodal model from Alibaba that can handle up to one million tokens in a single request.Jul 2026—1M$0.030 / $0.13per 1Mvia OpenRouter—Qwen3.7 PlusQwenQwen 3.7 is a proprietary text-and-image model from Alibaba with a one-million-token request limit and measured coding strength.Jun 2026—1M$0.32 / $1.28per 1Mvia OpenRouter—Qwen3.7 MaxQwenQwen 3.7 Max is Alibaba's proprietary flagship text model, released in May 2026 with a one-million-token request limit and strong measured coding performance.May 2026—1M$1.25 / $3.75per 1Mvia Novita AI—
Qwen3.65 sizes here
Qwen3.6 FlashQwenQwen3.6 Flash is a proprietary multimodal model from Alibaba that handles text, images and video in a single request and can work with up to one million tokens at once.Apr 2026—1M$0.19 / $1.13per 1Mvia OpenRouter—Qwen3.6 Max PreviewQwenQwen3.6 Max Preview is Alibaba's hosted-only flagship with a 262,144-token request limit and measured strength in coding tasks.Apr 2026—262K$1.03 / $6.16per 1Mvia OpenRouter—Qwen3.6 27BQwenAlibaba's 27-billion-parameter mid-size model can be downloaded, released in 2026.Apr 202627.8B262K$0.29 / $2.40per 1Mvia OpenRouter—Qwen3.6 35B A3BQwenQwen 3.6 is a downloadable mixture-of-experts model with only 3 billion active parameters for each token it processes, drawn from 36 billion total.Apr 202636B / 3B262K$0.14 / $1.00per 1Mvia OpenRouter—Qwen3.6 PlusQwenQwen 3.6 Plus is a hosted-only multimodal model from Alibaba that handles up to one million tokens in a single request and accepts text, images and video.Apr 2026—1M$0.33 / $1.95per 1Mvia OpenRouter—Qwen3.53 sizes here
Qwen3.5 Plus 2026-04-20QwenQwen 3.5 Plus is a hosted-only multimodal model from Alibaba that accepts text, images and video across a one-million-token request limit.Apr 2026—1M$0.30 / $1.80per 1Mvia OpenRouter—Qwen3.5 397B A17BQwenQwen 3.5 is a large downloadable model from Alibaba with a permissive Apache licence and a mixture-of-experts design that keeps 17 billion parameters active per token.Feb 2026403B / 17B262K$0.39 / $2.34per 1Mvia OpenRouter—Qwen3.5 Plus 2026-02-15QwenQwen 3.5 Plus is a proprietary multimodal model from Alibaba that accepts text, images and video across a one-million-token request limit.Feb 2026—1M$0.26 / $1.56per 1Mvia OpenRouter—Qwen3.5-9BQwenAlibaba's 9-billion-parameter small downloadable model has a permissive Apache licence and an unusually large request limit for its size.Feb 20269.7B262K$0.10 / $0.15per 1Mvia OpenRouter—Qwen3.5-FlashQwenQwen 3.5 Flash is a proprietary multimodal model from Alibaba that handles up to one million tokens in a single request across text, images and video.Feb 2026—1M$0.065 / $0.26per 1Mvia OpenRouter—Qwen3.5-35B-A3BQwenQwen3.5-35B-A3B is a downloadable model from Alibaba's Qwen line that activates only 3 billion of its 36 billion parameters for each word it processes, making it unusually efficient to run locally while keeping a permissive Apache licence. It handles text, images and video in a single request of up to 262,144 tokens, and scores well on coding tasks though creative writing is its weakest area.Feb 202636B / 3B262K$0.14 / $1.00per 1Mvia OpenRouter—Qwen3.5-122B-A10BQwenQwen3.5-122B-A10B is a large downloadable model from Alibaba that uses a mixture-of-experts design, activating only 10 billion of its 125.1 billion parameters for each token.Feb 2026125B / 10B262K$0.26 / $2.08per 1Mvia OpenRouter—Qwen3.5-27BQwenQwen3.5-27B is a 27.8-billion-parameter multimodal model from Alibaba that accepts text, images and video under a permissive Apache licence.Feb 202627.8B262K$0.20 / $1.56per 1Mvia OpenRouter—Qwen39 sizes here
Qwen3 Max ThinkingQwenQwen3 Max Thinking is a proprietary reasoning model from Alibaba that handles up to 262,144 tokens in a single request.Feb 2026—262K$0.78 / $3.90per 1Mvia OpenRouter—Qwen3 MaxQwenQwen 3 Max is a hosted-only text model from Alibaba with a 262,144-token request limit and measured coding strength on the Arena leaderboard.Sept 2025—262K$0.78 / $3.90per 1Mvia OpenRouter—Qwen3 30B A3B Thinking 2507QwenQwen3 is a thinking model from Alibaba with 30.5 billion total parameters but only 3 billion active per forward pass, released under an Apache licence.Jul 202530.5B / 3B82K$0.13 / $1.56per 1Mvia Alibaba Cloud147 tok/sQwen3 30B A3B Instruct 2507QwenQwen 3 is a text-only model from Alibaba with a mixture-of-experts design that keeps only 3 billion parameters active for each word while drawing on 30.5 billion total.Jul 202530.5B / 3B262K$0.048 / $0.19per 1Mvia OpenRouter—Qwen3 235B A22B Thinking 2507QwenQwen3 is a large downloadable model built for coding and long-document reasoning, with 22 billion of its 235 billion parameters active on each token.Jul 2025235B / 22B262K$0.23 / $2.30per 1Mvia OpenRouter—Qwen3 235B A22B Instruct 2507QwenQwen3 is a large mixture-of-experts model from Alibaba with 235.1 billion total parameters and 22 billion active per token, released in July 2025 under a permissive Apache licence.Jul 2025235B / 22B262K$0.15 / $0.60per 1Mvia OpenRouter—Qwen3 8BQwenQwen3 is a small downloadable text model released in 2025 with a permissive Apache licence and a 131,072-token request limit.Apr 20258.2B131K$0.12 / $0.46per 1Mvia OpenRouter—Qwen3 32BQwenQwen3 is a 32.8-billion-parameter text model released in 2025 with a permissive Apache licence.Apr 202532.8B131K$0.080 / $0.28per 1Mvia OpenRouter—Qwen3 14BQwenQwen3 is a compact downloadable text model from Alibaba with a permissive Apache licence and a 131,072-token request limit.Apr 202514.8B131K$0.23 / $0.91per 1Mvia OpenRouter—Qwen3 Coder NextQwenQwen3 Coder Next is a large downloadable code-specialist model with a permissive Apache licence and a 262,144-token request limit.Jan 202679.7B262K$0.12 / $0.80per 1Mvia OpenRouter—Qwen3 VL7 sizes here
Qwen3 VL 32B InstructQwenQwen3 VL is a vision-language model from Alibaba that accepts text and images and returns text.Oct 202533.4B131K$0.10 / $0.42per 1Mvia OpenRouter—Qwen3 VL 8B InstructQwenQwen3 VL is a compact vision-language model from Alibaba that accepts text and images and returns text.Oct 20258.8B262K$0.12 / $0.46per 1Mvia OpenRouter—Qwen3 VL 8B ThinkingQwenQwen3 VL is a compact vision-language model from Alibaba that can reason through its answers before responding.Oct 20258.8B131K$0.12 / $1.36per 1Mvia Alibaba Cloud132 tok/sQwen3 VL 30B A3B InstructQwenQwen3 VL is a vision-language model from Alibaba that accepts text and images and returns text.Sept 202531.1B / 3B262K$0.15 / $0.60per 1Mvia OpenRouter—Qwen3 VL 30B A3B ThinkingQwenQwen3 VL is a vision-language model from Alibaba that can be downloaded under a permissive Apache licence.Sept 202531.1B / 3B262K$0.20 / $2.40per 1Mvia OpenRouter—Qwen3 VL 235B A22B ThinkingQwenQwen3 VL is a large multimodal model from Alibaba whose weights can be downloaded under a permissive Apache licence.Sept 2025236B / 22B131K$0.26 / $2.60per 1Mvia Alibaba Cloud—Qwen3 VL 235B A22B InstructQwenQwen3 VL is a vision-language model from Alibaba whose weights can be downloaded under a permissive Apache licence.Sept 2025236B / 22B262K$0.21 / $1.90per 1Mvia OpenRouter—Qwen3 Coder4 sizes here
Qwen3 Coder PlusQwenQwen3 Coder Plus is a proprietary coding model from Alibaba's Qwen line that can handle up to one million tokens in a single request.Sept 2025—1M$0.65 / $3.25per 1Mvia OpenRouter—Qwen3 Coder FlashQwenQwen3 Coder Flash is a hosted-only coding model from Alibaba that can handle up to one million tokens in a single request.Sept 2025—1M$0.20 / $0.97per 1Mvia OpenRouter—Qwen3 Coder 30B A3B InstructQwenQwen3 Coder is a text-only coding model from Alibaba with a permissive Apache licence.Jul 202530.5B / 3B262K$0.070 / $0.27per 1Mvia OpenRouter—Qwen3 Coder 480B A35BQwenJul 2025480B / 35B262K$0.30 / $1.00per 1Mvia OpenRouter—Qwen3 Next2 sizes here
Qwen3 Next 80B A3B ThinkingQwenQwen3 Next is a thinking model from Alibaba with 81.3 billion total parameters and only 3 billion active per token, available under a permissive Apache licence.Sept 202581.3B / 3B262K$0.15 / $1.20per 1Mvia OpenRouter—Qwen3 Next 80B A3B InstructQwenQwen3 Next is a downloadable text model from Alibaba with an Apache licence and a 262,144-token request limit.Sept 202581.3B / 3B262K$0.090 / $1.10per 1Mvia OpenRouter—Qwen Plus 0728QwenA proprietary text model from Qwen built for document-scale work with a one-million-token request limit.Sept 2025—1M$0.26 / $0.78per 1Mvia OpenRouter—Qwen2.5 VL 72B InstructQwenQwen2.5 VL is a large vision-language model that accepts text and images and can handle up to 128,000 tokens in a single request.Jan 202573.4B128K$0.80 / $1.00per 1Mvia OpenRouter—Qwen2.5 Coder 32B InstructQwenQwen2.5 Coder is a 32.8-billion-parameter coding specialist with a permissive Apache licence.Nov 202432.8B33K$0.66 / $1.00per 1Mvia OpenRouter—Qwen2.52 sizes here
Qwen2.5 7B InstructQwenQwen 2.5 is a compact downloadable text model with a permissive Apache licence and a 32,768-token request limit.Sept 20247.6B33K$0.040 / $0.10per 1Mvia OpenRouter—Qwen2.5 72B InstructQwenQwen 2.5 is a 72.7-billion-parameter text-only instruction model released in September 2024.Sept 202472.7B33K$0.36 / $0.40per 1Mvia OpenRouter—