Model Platform
deepseek-ai/deepseek-v3.2
Fastest, most cost-effective model from DeepSeek Ai.
LLMNEWHOT
LLM
Fastest, most cost-effective model from DeepSeek Ai.
All You Need to Know About This Model
Overview:
Model Provider:DEEPSEEK
Model Type:Large Language Model
Deployment:Inferencing API; Playground
Pricing:$0.26/M Input & $0.38/M Output
Key Specs:
Parameters:-
Context:163k tokens
Architecture Type:Mixture-of-Experts (MoE)
Knowledge Cutoff:-
NEW
HOT
Fastest, most cost-effective model from DeepSeek Ai.
LLM
DeepSeek V3.2 Speciale
163.8K CONTEXT:
Input type:
Output type:
Context:163.84K
Input:$0.28/M tokens
Output:$0.4/M tokens
Max Output:65.54K
$0.28/0.4M in/out
NEW
HOT
Fastest, most cost-effective model from DeepSeek Ai.
LLM
DeepSeek V3.2 Exp
163.8K CONTEXT:
Input type:
Output type:
Context:163.84K
Input:$0.21/M tokens
Output:$0.32/M tokens
Max Output:65.54K
$0.21/0.32M in/out
NEW
DeepSeek's updated V3 model released on 03/24/2025.
LLM
DeepSeek-V3-0324
131.1K CONTEXT:
Input type:
Output type:
Context:131.07K
Input:$0.216/M tokens
Output:$0.88/M tokens
Max Output:131.07K
$0.216/0.88M in/out
NEW
HOT
The advanced LLM
LLM
DeepSeek-R1-0528
131.1K CONTEXT:
Input type:
Output type:
Context:131.07K
Input:$0.45/M tokens
Output:$2.15/M tokens
Max Output:131.07K
$0.45/2.15M in/out
Inizia con Oltre 300 Modelli,
Solo su Atlas Cloud.
