GitHub

Model	Providers	Speed	Latency
qwen/qwen3.5-397b-a17b阿里巴巴Free ReasoningToolsFilesOpen Weights	91VIP API wuer的api站 APDSM +3 moreShow fewer MineWuer API C85 API 温云	N/A	N/A
qwen3-coder-480b-a35b-instructQwenFree ToolsOpen Weights256K262K	+4 moreShow fewer	N/A	N/A
qwen-72bQwenFree 文本		N/A	N/A
qwen3.7-max-thinking阿里巴巴Free		N/A	N/A
qwen3.5-122b-a10b阿里巴巴Free		N/A	N/A
Qwen/Qwen2.5-Coder-7B-Instruct阿里巴巴Free		N/A	N/A
deepseek-ai/DeepSeek-R1-0528-Qwen3-8BDeepSeekFree		N/A	N/A
qwen2.5-coder-32b-instructVultrFree ToolsOpen Weights13K	+1 moreShow fewer	N/A	N/A
qwen/qwen3-next-80b-a3b-instruct阿里巴巴Free		N/A	N/A
qwen3.5-4阿里巴巴Free		N/A	N/A
qwen3.6-max阿里巴巴Free		N/A	N/A
qwen3.5-397b-a17bAlibaba (China)Free ReasoningToolsOpen WeightsVision	+3 moreShow fewer	N/A	N/A
qwen2.5-72b-instructQwenFree 文本		N/A	N/A
qwen3-235b-a22b-instructiFlowFree ToolsOpen Weights256K		N/A	N/A
qwen3-235b-a22b-instruct-2507ScalewayFree ToolsOpen Weights128KTools		N/A	N/A
Qwen/Qwen2.5-7B-InstructSiliconFlow (China)Free Tools33K		N/A	N/A
qwen3-30b-a3b-fp8阿里巴巴Free		N/A	N/A
qwen3-embedding-0.6b阿里巴巴Free		N/A	N/A
qwen/qwen3-next-80b-a3b-instruct:free阿里巴巴Free		N/A	N/A
QwenFree Tools131.1K英伟达Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...	+10 moreShow fewer	N/A	N/A
qwen3-reranker-0.6b阿里巴巴Free		N/A	N/A
qwen3-reranker-4b阿里巴巴Free		N/A	N/A
qwen3.7-max-t阿里巴巴Free		N/A	N/A
qwen3.5-397b-a17b-t阿里巴巴Free		N/A	N/A
qwen3.6-35b百炼QwenFree		N/A	N/A
qwen3-reranker-8b阿里巴巴Free		N/A	N/A
qwen3-235b-thinking百炼QwenFree		N/A	N/A
qwen3-1.7b阿里巴巴Free		N/A	N/A
qwen3-235b-Instruct百炼QwenFree		N/A	N/A
QwenFree Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...		N/A	N/A
QwenFree Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...	+1 moreShow fewer	N/A	N/A
QwenFree Tools262KOpen Weights128KQwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...	+1 moreShow fewer	N/A	N/A
qwen-7b-chatAliyun(Qwen)Free		N/A	N/A
qwen-audio-chat阿里巴巴Free		N/A	N/A
qwen-image-2.0阿里巴巴Free		N/A	N/A
qwen-audio-turbo阿里巴巴Free		N/A	N/A
qwen-math-plusAlibaba (China)Free Tools4.1KTools		N/A	N/A
qwen-max-longcontext阿里巴巴Free		N/A	N/A
qwen-plus-2024-11-25阿里巴巴Free		N/A	N/A
qwen-math-plus-2024-08-16阿里巴巴Free		N/A	N/A
qwen-longAlibaba (China)Free Tools10M		N/A	N/A
qwen-plus-2024-08-06阿里巴巴Free		N/A	N/A
qwen-max-2024-09-19阿里巴巴Free		N/A	N/A
qwen-14b-chatAliyun(Qwen)Free		N/A	N/A
qwen-mt-flashQwenFree		N/A	N/A
qwen-plus-2024-07-23阿里巴巴Free		N/A	N/A
qwen-plus-2024-09-19阿里巴巴Free		N/A	N/A
Qwen3-1.7B-free阿里巴巴Free		N/A	N/A
qwen-audio-turbo-2024-12-04阿里巴巴Free		N/A	N/A
qwen-image-2.0-pro阿里巴巴Free		N/A	N/A
qwen-audio-turbo-2024-08-07阿里巴巴Free		N/A	N/A
qwen-vl-plusAlibaba (China)Free ToolsMultimodal131.1K		N/A	N/A
qwen-image-edit阿里巴巴Free		N/A	N/A
Qwen3-30B-A3B-Instruct-2507阿里巴巴Free		N/A	N/A
qwen-mt-plusAlibaba (China)Free 16.4K		N/A	N/A
Qwen3-Next-80B-A3B-Instruct阿里巴巴Free		N/A	N/A
qwen-72b-chat阿里巴巴Free		N/A	N/A
qwen-maxAlibaba (China)Free Tools131.1K		N/A	N/A
qwen-mt-turboAlibaba (China)Free 16.4K		N/A	N/A
Qwen3-VL-235B-A22B-Instruct阿里巴巴Free		N/A	N/A

Free Qwen API

Other Model Families