Aliyun Models - CometAPI

Q

Qwen3.6-Plus

Input:$0.32/M

Output:$1.92/M

Qwen 3.6-Plus is now available, featuring enhanced code development capabilities and improved efficiency in multimodal recognition and inference, making the Vibe Coding experience even better.

Q

Qwen 3.5 Flash

Q

Qwen 3.5 Flash

Input:$0.16/M

Output:$0.96/M

The Qwen-3.5 Flash Series is a production-oriented family of large language models (LLMs) developed by the Alibaba Group under its Qwen initiative. It represents the deployment (hosted/API) layer of the broader Qwen-3.5 model family, optimized for high speed, long-context processing, and agent-based applications. In simple terms: Qwen-3.5 Flash = fast, scalable, long-context, tool-using versions of Qwen-3.5 models designed for real-world production use.

Q

qwen3.5-plus

Input:$0.32/M

Output:$1.92/M

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency.

Q

qwen3.5-397b-a17b

Input:$0.48/M

Output:$2.88/M

The Qwen3.5 series 397B-A17B 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.

Q

qwen3 max

Input:$0.8/M

Output:$3.2/M

- qwen3-max: Alibaba Tongyi Qianwen team's latest Qwen3-Max model, positioned as the series' performance peak. - 🧠 Powerful Multimodal and Inference: Supports ultra-long context (up to 128k tokens) and Multimodal input, excels at complex Inference, code generation, translation, and creative content. - ⚡️ Breakthrough Improvement: Significantly optimized across multiple technical indicators, faster response speed, knowledge cutoff up to 2025, suitable for enterprise-level high-precision AI applications.

Q

Qwen Image

Q

Qwen Image

Per Request:$0.028

Qwen-Image is a revolutionary image generation foundational model released by Alibaba's Tongyi Qianwen team in 2025. With a parameter scale of 20 billion, it is based on the MMDiT (Multimodal Diffusion Transformer) architecture. The model has achieved significant breakthroughs in complex text rendering and precise image editing, demonstrating exceptional performance particularly in Chinese text rendering. Translated with DeepL.com (free version)

Q

qwen3-vl-32b

Q

qwen3-vl-32b

Input:$0.24/M

Output:$0.96/M

Qwen3-VL-32B is the 32-billion-parameter dense variant in Alibaba’s Qwen3 vision-language model family. It is a multimodal (vision + language + video) transformer designed for unified perception, long-context reasoning, robust OCR and visual grounding, and agentic/toolified workflows.

Q

qwen3-vl-30b-a3b

Q

qwen3-vl-30b-a3b

Context:2M

Input:$0.12/M

Output:$0.48/M

Qwen3-VL-30B-A3B is a state-of-the-art multimodal AI model in the Qwen3 AI family, developed by Alibaba’s Qwen team. It’s designed to unify language understanding and visual comprehension — including text, images, and video — in a single foundation model.

Q

qwen3-vl-235b-a22b

Q

qwen3-vl-235b-a22b

Context:2M

Input:$0.24/M

Output:$0.96/M

qwen3-vl-235b-a22b 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 of real-world/synthetic categories, 2D/3D spatial grounding, and long-form visual comprehension, achieving competitive multimodal benchmark results.

Q

qwen3-coder-plus-2025-07-22

Q

qwen3-coder-plus-2025-07-22

Input:$0.52/M

Output:$2.6/M

Qwen3 Coder Plus stable version, released on July 22, 2025, provides higher stability, suitable for production deployment.

Q

qwen3-coder-plus

Q

qwen3-coder-plus

Input:$0.52/M

Output:$2.6/M

Q

qwen3-coder-480b-a35b-instruct

Q

qwen3-coder-480b-a35b-instruct

Input:$0.24/M

Output:$0.96/M

Q

qwen3-coder

Q

qwen3-coder

Input:$0.24/M

Output:$0.96/M

Q

qwen3-8b

Q

qwen3-8b

Input:$0.04/M

Output:$0.16/M

Q

qwen3-32b

Q

qwen3-32b

Input:$1.6/M

Output:$6.4/M

Q

qwen3-30b-a3b

Q

qwen3-30b-a3b

Input:$0.12/M

Output:$0.48/M

Has 3 billion parameters, balancing performance and resource requirements, suitable for enterprise-level applications. - This model may employ MoE or other optimized architectures, suitable for scenarios requiring efficient processing of complex tasks, such as intelligent customer service and content generation.

Q

qwen3-235b-a22b

Q

qwen3-235b-a22b

Input:$0.336/M

Output:$1.344/M

Qwen3-235B-A22B is the flagship model of the Qwen3 series, with 23.5 billion parameters, using a Mixture of Experts (MoE) architecture. - Particularly suitable for complex tasks requiring high-performance Inference, such as coding, mathematics, and Multimodal applications.

Q

qwen3-14b

Q

qwen3-14b

Input:$0.8/M

Output:$3.2/M

Q

qwen2.5-vl-72b-instruct

Q

qwen2.5-vl-72b-instruct

Input:$2.4/M

Output:$7.2/M

Q

qwen2.5-vl-72b

Q

qwen2.5-vl-72b

Input:$2.4/M

Output:$7.2/M

Q

qwen2.5-vl-32b-instruct

Q

qwen2.5-vl-32b-instruct

Input:$2.4/M

Output:$7.2/M

Q

qwen2.5-omni-7b

Q

qwen2.5-omni-7b

Input:$60/M

Output:$60/M

Q

qwen2.5-math-72b-instruct

Q

qwen2.5-math-72b-instruct

Input:$3.2/M

Output:$12.8/M

Q

qwen2.5-coder-7b-instruct

Q

qwen2.5-coder-7b-instruct

Input:$0.8/M

Output:$3.2/M

Q

qwen2.5-coder-32b-instruct

Q

qwen2.5-coder-32b-instruct

Input:$0.8/M

Output:$3.2/M

Q

qwen2.5-7b-instruct

Q

qwen2.5-7b-instruct

Input:$0.8/M

Output:$3.2/M

Q

qwen2.5-72b-instruct

Q

qwen2.5-72b-instruct

Input:$3.2/M

Output:$3.2/M

Q

qwen2.5-32b-instruct

Q

qwen2.5-32b-instruct

Input:$0.96/M

Output:$3.84/M

Q

qwen2.5-14b-instruct

Q

qwen2.5-14b-instruct

Input:$3.2/M

Output:$12.8/M

Q

qwen2-vl-7b-instruct

Q

qwen2-vl-7b-instruct

Input:$1.6/M

Output:$6.4/M

Q

qwen2-vl-72b-instruct

Q

qwen2-vl-72b-instruct

Input:$1.6/M

Output:$6.4/M

Q

qwen2-7b-instruct

Q

qwen2-7b-instruct

Input:$0.16/M

Output:$0.64/M

Q

qwen2-72b-instruct

Q

qwen2-72b-instruct

Input:$8/M

Output:$32/M

Q

qwen2-57b-a14b-instruct

Q

qwen2-57b-a14b-instruct

Input:$3.2/M

Output:$12.8/M

Q

qwen2-1.5b-instruct

Q

qwen2-1.5b-instruct

Input:$0.16/M

Output:$0.64/M

Q

qwen1.5-7b-chat

Q

qwen1.5-7b-chat

Input:$0.16/M

Output:$0.64/M

Q

Qwen OCR

Q

Qwen OCR

Input:$1.6/M

Output:$6.4/M

Q

qwen-image-2

Q

qwen-image-2

Coming soon

Input:$60/M

Output:$240/M

qwen-image-2 coming soon

Q

Qwen2.5-72B-Instruct-128K

Q

Qwen2.5-72B-Instruct-128K

Input:$3.2/M

Output:$3.2/M