Sign up
All models
DeepSeek V3.2

DeepSeek V3.2

DeepSeek

Latest DeepSeek model hosted in the US.

Try on Simtheory
Qwen 3.6 Plus Frontier Claude 3.7 Sonnet Frontier Claude 3.7 Sonnet (high output) Frontier Claude 3.7 Sonnet (thinking) Frontier Claude 4.5 Opus Frontier Claude 4.5 Sonnet Frontier Claude 4.5 Sonnet (thinking) Frontier Claude 4.6 Opus Frontier Claude 4.6 Opus Max Frontier Claude 4.6 Sonnet Frontier

Specifications

Context window 163,840 tokens
Max output 32,000 tokens
Knowledge cutoff September 2025
Multipart messages No
Vision capabilities No

Default Parameters

Temperature 0.3
Top P 1.0
Frequency penalty 0.0
Presence penalty 0.0
Top K 50

More from DeepSeek

DeepSeek-R1

DeepSeek-R1

Deep reasoning model from DeepSeek hosted securely in the USA

131,072 ctx 8,192 out