Tongyi DeepResearch 30B A3B

About 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 Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Alibaba Qwen Model Lineup

Compare all models from Alibaba Qwen to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

InternVL3 78B

Other

Input: $0.10

Output: $0.39

Context: -

Hermes 4 70B

Nous Research

Input: $0.11

Output: $0.38

Context: 131k

GPT-4.1 Nano

OpenAI

Input: $0.10

Output: $0.40

Context: 1.0M

Gemini 2.0 Flash

Google

Input: $0.10

Output: $0.40

Context: 1.0M

💡 Cheaper Alternatives

Same Brand (Alibaba Qwen)

Cross Brand

🚀 Quick Start

Get started with Tongyi DeepResearch 30B A3B API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="alibaba/tongyi-deepresearch-30b-a3b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision