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

Open and Advanced Models.

LLMFP8NEW
Beranda
Jelajahi
Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
LLM

Open and Advanced Models.

Semua yang Perlu Anda Ketahui Tentang Model Ini

Gambaran Umum:

Penyedia Model:Qwen by Alibaba
Tipe Model:Model Bahasa Besar
Deployment:API Inferensi; Playground
Harga:$0.09/M Input & $0.45/M Output

Spesifikasi Utama:

Parameter:-
Konteks:131k token
Tipe Arsitektur:-
Batas Pengetahuan:-

Keunggulan Utama:

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

Kasus Penggunaan:

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

Jelajahi Model Serupa

HOT
Qwen3-VL-235B-A22B-Instruct

Tidak ada deskripsi tersedia.

LLM

Qwen3-VL-235B-A22B-Instruct

131.1K KONTEKS:
Tipe input:
input type icons
Tipe output:
output type icons
Konteks:131.07K
Input:$0.3/M token
Output:$1.5/M token
Output Maks:32.77K
$0.3/1.5M masuk/keluar
NEW
Qwen3 30B A3B Instruct 2507

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

LLM

Qwen3 30B A3B Instruct 2507

131.1K KONTEKS:
Tipe input:
input type icons
Tipe output:
output type icons
Konteks:131.07K
Input:$0.09/M token
Output:$0.3/M token
Output Maks:131.07K
$0.09/0.3M masuk/keluar
NEW
HOT
Qwen3 Next 80B A3B Thinking

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

LLM

Qwen3 Next 80B A3B Thinking

262.1K KONTEKS:
Tipe input:
input type icons
Tipe output:
output type icons
Konteks:262.14K
Input:$0.15/M token
Output:$1.5/M token
Output Maks:262.14K
$0.15/1.5M masuk/keluar
NEW
HOT
Qwen3 Next 80B A3B Instruct

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

LLM

Qwen3 Next 80B A3B Instruct

262.1K KONTEKS:
Tipe input:
input type icons
Tipe output:
output type icons
Konteks:262.14K
Input:$0.15/M token
Output:$1.5/M token
Output Maks:262.14K
$0.15/1.5M masuk/keluar
Mulai dari 300+ Model,

Hanya di Atlas Cloud.