Alibaba-NLP/Tongyi-DeepResearch-30B-A3B

Open and Advanced Models.

LLMFP8NEW
Hem
Utforska
Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
LLM

Open and Advanced Models.

Allt Du Behöver Veta Om Denna Modell

Översikt:

Modellleverantör:Qwen by Alibaba
Modelltyp:Stor Språkmodell
Driftsättning:Inferens-API; Playground
Prissättning:$0.09/M Input & $0.45/M Output

Nyckelspecifikationer:

Parametrar:-
Kontext:131k tokens
Arkitekturtyp:-
Kunskapsavbrott:-

Kärnstyrkor:

Optimized for deep research tasks
Advanced agentic training
Dual inference paradigms (ReAct/Heavy)
Efficient 30B MoE (3B active)

Användningsfall:

Agentic search & research
Complex long-horizon problem-solving
Heavy inference workflows
Tool-using agent applications

Utforska Liknande Modeller

HOT
Qwen3-VL-235B-A22B-Instruct

Ingen beskrivning tillgänglig.

LLM

Qwen3-VL-235B-A22B-Instruct

131.1K KONTEXT:
Inmatningstyp:
input type icons
Utmatningstyp:
output type icons
Kontext:131.07K
Inmatning:$0.3/M tokens
Utmatning:$1.5/M tokens
Max Utmatning:32.77K
$0.3/1.5M in/ut
NEW
Qwen3 30B A3B Instruct 2507

Qwen's latest and most powerful open-source model.

LLM

Qwen3 30B A3B Instruct 2507

131.1K KONTEXT:
Inmatningstyp:
input type icons
Utmatningstyp:
output type icons
Kontext:131.07K
Inmatning:$0.09/M tokens
Utmatning:$0.3/M tokens
Max Utmatning:131.07K
$0.09/0.3M in/ut
NEW
HOT
Qwen3 Next 80B A3B Thinking

Qwen's latest and most powerful open-source model.

LLM

Qwen3 Next 80B A3B Thinking

262.1K KONTEXT:
Inmatningstyp:
input type icons
Utmatningstyp:
output type icons
Kontext:262.14K
Inmatning:$0.15/M tokens
Utmatning:$1.5/M tokens
Max Utmatning:262.14K
$0.15/1.5M in/ut
NEW
HOT
Qwen3 Next 80B A3B Instruct

Qwen's latest and most powerful open-source model.

LLM

Qwen3 Next 80B A3B Instruct

262.1K KONTEXT:
Inmatningstyp:
input type icons
Utmatningstyp:
output type icons
Kontext:262.14K
Inmatning:$0.15/M tokens
Utmatning:$1.5/M tokens
Max Utmatning:262.14K
$0.15/1.5M in/ut
Börja från 300+ Modeller,

Endast på Atlas Cloud.