Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
Open and Advanced Models.
LLMFP8NEW
LLM
Open and Advanced Models.
Loading...
All You Need to Know About This Model
Overview:
Model Provider:Qwen by Alibaba
Model Type:Large Language Model
Deployment:Inferencing API; Playground
Pricing:$0.09/M Input & $0.45/M Output
Key Specs:
Parameters:-
Context:131k tokens
Architecture Type:-
Knowledge Cutoff:-
Core Strengths:
Optimized for deep research tasks
Advanced agentic training
Dual inference paradigms (ReAct/Heavy)
Efficient 30B MoE (3B active)
Use Cases:
Agentic search & research
Complex long-horizon problem-solving
Heavy inference workflows
Tool-using agent applications
HOT
No description available.
LLM
Qwen3-VL-235B-A22B-Instruct
131.1K CONTEXT
Input type:
Output type:
Context:131.07K
Input:$0.3/M tokens
Output:$1.5/M tokens
Max Output:32.77K
$0.3/1.5M IN/OUT
NEW
Qwen's latest and most powerful open-source model.
LLM
Qwen3 30B A3B Instruct 2507
131.1K CONTEXT
Input type:
Output type:
Context:131.07K
Input:$0.09/M tokens
Output:$0.3/M tokens
Max Output:131.07K
$0.09/0.3M IN/OUT
NEW
HOT
Qwen's latest and most powerful open-source model.
LLM
Qwen3 Next 80B A3B Thinking
262.1K CONTEXT
Input type:
Output type:
Context:262.14K
Input:$0.15/M tokens
Output:$1.5/M tokens
Max Output:262.14K
$0.15/1.5M IN/OUT
NEW
HOT
Qwen's latest and most powerful open-source model.
LLM
Qwen3 Next 80B A3B Instruct
262.1K CONTEXT
Input type:
Output type:
Context:262.14K
Input:$0.15/M tokens
Output:$1.5/M tokens
Max Output:262.14K
$0.15/1.5M IN/OUT
Start From 300+ Models,
Only at Atlas Cloud.
