Tongyi DeepResearch Models by Alibaba
1 model2025Up to 131k ctx
About
Alibaba's Tongyi DeepResearch is a series of reasoning-focused language models designed for deep research tasks, featuring sparse MoE architecture with a small active parameter footprint.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
1 in view
Tongyi DeepResearch 30B A3BCurrent
Use when the workload needs 131k context and 30B parameters.
2025-03131k context30B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Tongyi DeepResearch 30B A3B | Use when the workload needs 131k context and 30B parameters. | 2025-03 | 131k context30B parameters | Current |
Release Timeline
1 release group2025-03
1 current
Tongyi DeepResearch 30B A3B
Current131k context30B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Tongyi DeepResearch 30B A3B | 2025-03 | 131k | 30B |
Frequently Asked Questions
- What is Tongyi DeepResearch used for?
- Alibaba's Tongyi DeepResearch is a series of reasoning-focused language models designed for deep research tasks, featuring sparse MoE architecture with a small active parameter footprint.
- How does Tongyi DeepResearch compare to Qwen-MT?
- Tongyi DeepResearch by Alibaba is strongest where you need its listed use cases, while Qwen-MT by Alibaba is the closest related family to check for adjacent model selection. Tongyi DeepResearch has 1 listed variant and reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which Tongyi DeepResearch model should I use?
- If price is the main constraint, use the pricing table first because Tongyi DeepResearch does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Tongyi DeepResearch 30B A3B with 131k context.
