# Tongyi DeepResearch 30B A3B Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks and delivers state-of-the-art performance on benchmarks like Humanity's Last Exam, BrowserComp, BrowserComp-ZH, WebWalkerQA, GAIA, xbench-DeepSearch, and FRAMES. This makes it superior for complex agentic search, reasoning, and multi-step problem-solving compared to prior models. The model includes a fully automated synthetic data pipeline for scalable pre-training, fine-tuning, and reinforcement learning. It uses large-scale continual pre-training on diverse agentic data to boost reasoning and stay fresh. It also features end-to-end on-policy RL with a customized Group Relative Policy Optimization, including token-level gradients and negative sample filtering for stable training. The model supports ReAct for core ability checks and an IterResearch-based 'Heavy' mode for max performance through test-time scaling. It's ideal for advanced research agents, tool use, and heavy inference workflows. ## Model Information - **Organization**: [Alibaba](/llm.txt) - **Slug**: tongyi-deepresearch-30b-a3b - **Available at Providers**: 10 - **Release Date**: September 18, 2025 ## Providers | Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link | |----------|------|-----------------|------------------|------|------| | [Nano-GPT](/llm/nanogpt.txt) | Tongyi DeepResearch 30B A3B | | | | | | [OpenRouter](/llm/openrouter.txt) | Tongyi DeepResearch 30B A3B | 0.09 | 0.45 | | [View](https://openrouter.ai/alibaba/tongyi-deepresearch-30b-a3b) | | [ValorGPT](/llm/valorgpt.txt) | AL | | | | [View](https://www.valorgpt.com/models/alibaba-tongyi-deepresearch-30b-a3b) | | [ValorGPT](/llm/valorgpt.txt) | AL | | | Yes | [View](https://www.valorgpt.com/models/alibaba-tongyi-deepresearch-30b-a3b-free) | | [Atlas Cloud](/llm/atlascloud.txt) | Tongyi DeepResearch 30B A3B | 0.09 | 0.45 | | [View](https://www.atlascloud.ai/models/Alibaba-NLP/Tongyi-DeepResearch-30B-A3B) | | [LangDB](/llm/langdb.txt) | tongyi-deepresearch-30b-a3b | | | | [View](https://langdb.ai/app/models) | | [Kilo Code](/llm/kilocode.txt) | Tongyi DeepResearch 30B A3B | 0.09 | 0.45 | | [View](https://kilo.ai/models/alibaba/tongyi-deepresearch-30b-a3b) | | [Blackbox AI](/llm/blackboxai.txt) | blackboxai/alibaba/tongyi-deepresearch-30b-a3b | | | | | | [WaveSpeed AI](/llm/wavespeed.txt) | tongyi-deepresearch-30b-a3b | 0.10 | 0.50 | | | | [Writingmate](/llm/writingmate.txt) | Tongyi DeepResearch 30B A3B | | | | [View](https://writingmate.ai/models/alibaba/tongyi-deepresearch-30b-a3b) | --- [← Back to all providers](/llm.txt)