tongyi-deepresearch-30b-a3bTongyi DeepResearch is a 30B-parameter agentic model (3B active per token) built for long-horizon, deep research and information-seeking tasks. It achieves state-of-the-art results on major agentic search and reasoning benchmarks, outperforming prior models in complex multi-step problem solving. Trained with a fully automated synthetic data pipeline and advanced on-policy RL, it supports ReAct workflows and a high-performance “Heavy” mode for test-time scaling, making it well suited for advanced research agents, tool use, and intensive inference workloads.
Select an endpoint and copy a working example for this model.
from openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.apertis.ai/v1") response = client.chat.completions.create( model="tongyi-deepresearch-30b-a3b", messages=[ {"role": "user", "content": "Hello!"} ], max_tokens=1024, temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(# model="tongyi-deepresearch-30b-a3b",# messages=[{"role": "user", "content": "Hello!"}],# extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )modelmessagesmax_tokenstemperaturetop_pstreamtoolsreasoning_effortstream_optionsthinkingextra_bodyUse these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.
See how this model compares to others from the same provider.
Qwen3.7-Plus is a cost-effective multimodal model in Alibaba's Qwen3.7 series, supporting text and image inputs with text output. It combines the series' strong language capabilities with significantly enhanced vision-language understanding, while retaining full-stack agent-level intelligence for coding, tool use, and productivity workflows. Its standout capability is multimodal interactive agency—the ability to perceive real-world scenes, understand screens and graphical interfaces, generate code from visual references, and perform end-to-end navigation within applications. This makes Qwen3.7-Plus well suited for GUI automation, visual coding, productivity agents, and multimodal task execution.
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series, designed for agent-centric workloads with strong performance in coding, productivity, and long-horizon autonomous execution. It supports text input and output and delivers notable improvements in coding and agentic capabilities over previous Qwen generations. Optimized for real-world workflows, the model also supports explicit prompt caching for efficient reuse of repeated context, making it well suited for scalable development, office automation, and advanced agent systems.
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse Mixture-of-Experts (MoE) architecture with approximately 1 trillion parameters. It is optimized for agentic coding, tool use, and long-context reasoning, supporting a 262K token context window. The model includes an integrated thinking mode that preserves reasoning across multi-turn interactions, along with support for structured outputs and function calling. Available exclusively via Alibaba Cloud Model Studio and Qwen Studio APIs, it is designed for high-performance, production-grade agent workflows.
See how this model compares to others from the same provider.
Qwen3-VL-8B-Instruct is a multimodal model for precise reasoning across text, images, and video. With improved fusion architectures (Interleaved-MRoPE, DeepStack, and text-timestamp alignment), it supports long-context understanding up to 1M tokens and handles tasks like document parsing, VQA, spatial reasoning, and GUI control. It delivers LLM-level text comprehension, stronger OCR across 32 languages, and robust performance across diverse visual conditions.
Qwen3-VL-235B-A22B Thinking is a powerful multimodal model that combines advanced text generation with strong image and video understanding, optimized for STEM and math reasoning. It offers robust perception, spatial grounding, and long-form visual comprehension, and supports agent-style interactions such as multi-image dialogue, video timeline alignment, GUI control, and visual-to-code workflows. With competitive benchmark results and strong text-only ability, it’s suited for production uses like document AI, OCR, UI assistance, spatial tasks, and vision-language research.
Qwen3.5 Vision-Language Flash models are built on a hybrid architecture that combines linear attention mechanisms with a sparse Mixture-of-Experts (MoE) design to achieve higher inference efficiency. Compared with the Qwen3 generation, the 3.5 Flash models deliver significant improvements in both pure-text reasoning and multimodal understanding. Optimized for fast response times, they strike a strong balance between inference speed and overall performance, making them well suited for real-time multimodal and agent-based applications.
Qwen3.5 Vision-Language Plus models are part of the native multimodal Qwen3.5 series, built on a hybrid architecture that combines linear attention mechanisms with sparse Mixture-of-Experts (MoE) designs to improve inference efficiency at scale. Across a wide range of evaluations, the series demonstrates performance comparable to leading state-of-the-art models. Compared with the Qwen3 generation, the 3.5 Plus models deliver significant improvements in both pure-text reasoning and multimodal understanding, making them well suited for applications that require strong performance across language, vision, and agent-based tasks.
Initialized observational baseline with no recorded failures