模型 · NovaRouter

Qwen: Qwen3.8 Max PrimeQwen3.8 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. It accepts…by Qwen · 2026年9月23日1M 上下文$4 输入$12 输出

Qwen: Qwen3.8 Omni FlashQwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video under…by Qwen · 2026年9月21日1M 上下文$0.15 输入$0.47 输出

Qwen: Qwen3.8 Max (0902)Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts…by Qwen · 2026年9月3日1M 上下文$2 输入$6 输出

Qwen: Qwen3.8 FlashQwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and…by Qwen · 2026年8月26日1M 上下文$0.15 输入$0.47 输出

Qwen: Qwen3.8 27BQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction…by Qwen · 2026年8月14日1M 上下文$0.04 输入$2.3 输出

Qwen3 Reranker 8BQwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance…by Qwen · 2026年8月13日41K 上下文免费输入免费输出

Qwen: Qwen3 ASR 1.7BQwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 langua…by Qwen · 2026年8月13日— 上下文$7.5 输入$0 输出

Qwen: Qwen3 ASR 0.6BQwen3 ASR 0.6B is a compact automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30…by Qwen · 2026年8月13日— 上下文$3.33 输入$0 输出

Qwen: Qwen3.8 2.4T A95BQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max (/qwen/qwen3.8-max), with 95…by Qwen · 2026年8月12日1M 上下文$2 输入$6 输出

Qwen: Qwen Image 3Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with…by Qwen · 2026年8月5日66K 上下文$0.003 / 张输入— 输出

Qwen: Qwen Image 3 ProQwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with ri…by Qwen · 2026年8月5日66K 上下文$0.003 / 张输入— 输出

Qwen: Qwen3.7 FlashQwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction,…by Qwen · 2026年7月27日1M 上下文$0.03 输入$0.13 输出

Qwen: Qwen-Audio-3.0-TTS FlashQwen-Audio-3.0-TTS Flash is Alibaba's fast, cost-efficient text-to-speech model, generating spoken audio from text via the DashScope Speech Synthesize…by Qwen · 2026年7月23日— 上下文$15 输入$0 输出

Qwen: Qwen-Audio-3.0-TTS PlusQwen-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.by Qwen · 2026年7月23日— 上下文$20 输入$0 输出

Qwen: Qwen3.7 PlusQwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text ca…by Qwen · 2026年6月3日1M 上下文$0.32 输入$1.28 输出

Qwen: Qwen3.7 MaxQwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with par…by Qwen · 2026年5月21日1M 上下文$1.48 输入$4.42 输出

Qwen: Qwen3.5 Plus 2026-04-20Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, w…by Qwen · 2026年4月27日1M 上下文$0.3 输入$1.8 输出

Qwen: Qwen3.6 FlashQwen3.6 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 win…by Qwen · 2026年4月27日1M 上下文$0.188 输入$1.13 输出

Qwen: Qwen3.6 35B A3BQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It u…by Qwen · 2026年4月27日262K 上下文$0.1 输入$0.95 输出

Qwen: Qwen3.6 27BQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabi…by Qwen · 2026年4月27日262K 上下文$0.32 输入$3.2 输出

Qwen: Qwen3.6 PlusQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalabi…by Qwen · 2026年4月2日1M 上下文$0.325 输入$1.95 输出

Qwen: Qwen3.5-9BQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an effi…by Qwen · 2026年3月10日262K 上下文$0.1 输入$0.15 输出

Qwen: Qwen3.5-35B-A3BThe Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a spa…by Qwen · 2026年2月25日262K 上下文$0.15 输入$1 输出

Qwen: Qwen3.5-27BThe Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference…by Qwen · 2026年2月25日262K 上下文$0.26 输入$2.6 输出

Qwen: Qwen3.5-122B-A10BThe Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixtur…by Qwen · 2026年2月25日262K 上下文$0.26 输入$2.08 输出

Qwen: Qwen3.5-FlashThe Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-…by Qwen · 2026年2月25日1M 上下文$0.065 输入$0.26 输出

Qwen: Qwen3.5 Plus 2026-02-15The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixtu…by Qwen · 2026年2月16日1M 上下文$0.26 输入$1.56 输出

Qwen: Qwen3.5 397B A17BThe Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse…by Qwen · 2026年2月16日262K 上下文$0.5 输入$3.6 输出

Qwen: Qwen3 Coder NextQwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with…by Qwen · 2026年2月4日262K 上下文$0.12 输入$0.8 输出

Qwen: Qwen3 Embedding 8BThe Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This…by Qwen · 2025年10月28日33K 上下文$0.01 输入$0 输出

Qwen: Qwen3 Embedding 4BThe Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This…by Qwen · 2025年10月28日33K 上下文$0.02 输入$0 输出

Qwen: Qwen3 VL 8B InstructQwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text,…by Qwen · 2025年10月14日262K 上下文$0.25 输入$0.75 输出

Qwen: Qwen3 VL 30B A3B ThinkingQwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking vari…by Qwen · 2025年10月6日262K 上下文$0.29 输入$1 输出

Qwen: Qwen3 VL 30B A3B InstructQwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct vari…by Qwen · 2025年10月6日262K 上下文$0.15 输入$0.6 输出

Qwen: Qwen3 VL 235B A22B InstructQwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video.…by Qwen · 2025年9月23日262K 上下文$0.21 输入$1.9 输出

Qwen: Qwen3 Coder FlashQwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing…by Qwen · 2025年9月17日1M 上下文$0.195 输入$0.975 输出

Qwen: Qwen3 Next 80B A3B ThinkingQwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed…by Qwen · 2025年9月11日262K 上下文$0.15 输入$1.2 输出

Qwen: Qwen3 Next 80B A3B InstructQwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces…by Qwen · 2025年9月11日262K 上下文$0.1 输入$1.1 输出

Qwen: Qwen3 Coder 30B A3B InstructQwen3-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 c…by Qwen · 2025年7月31日262K 上下文$0.07 输入$0.28 输出

Qwen: Qwen3 30B A3B Instruct 2507Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates i…by Qwen · 2025年7月29日262K 上下文$0.1 输入$0.3 输出