Atlas / Models / Alibaba / Tongyi DeepResearch 30B A3B

Tongyi DeepResearch 30B A3B✓ Catalog verified

alibaba/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.

Input price
$0.09 /1M
Output price
$0.45 /1M
Context
131K
Modalities
text
Released
Sep 18, 2025
Tool calling
✓ Yes
Atlas signal
89/100
01

Overview

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.

Access: available through the official Alibaba API. Context window: 131K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifieralibaba/tongyi-deepresearch-30b-a3b
ProviderAlibaba
Model typeText LLM
Context window131K catalog
Input modalitiestext
Output modalitiestext
ReleasedSep 18, 2025
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_p": null,
  "temperature": null,
  "frequency_penalty": null
}
03

Pricing

Live pricing components for alibaba/tongyi-deepresearch-30b-a3b as published in the catalog.

$0.09
Input /1M
$0.45
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$9e-8$0.09 / 1MPer input token
Completion tokens$4.5e-7$0.45 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.14Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Tongyi DeepResearch 30B A3B
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
87signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Tongyi DeepResearch 30B A3B through an OpenAI-compatible client.

from openai import OpenAI

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

response = client.chat.completions.create(
    model="alibaba/tongyi-deepresearch-30b-a3b",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Tongyi DeepResearch 30B A3B cost?

$0.09 per 1M input tokens and $0.45 per 1M output tokens on the official Alibaba API.

What is the context window of Tongyi DeepResearch 30B A3B?

Tongyi DeepResearch 30B A3B supports up to 131K tokens of context.

Does Tongyi DeepResearch 30B A3B support tool / function calling?

Yes, Tongyi DeepResearch 30B A3B supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Tongyi DeepResearch 30B A3B?

Use the official Alibaba API with the model id `alibaba/tongyi-deepresearch-30b-a3b`. See the Quick start section above for code examples.