deepseek

DeepSeek: DeepSeek V3.2 Exp

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Input Cost
$0.27
per 1M tokens
Output Cost
$0.41
per 1M tokens
Context Window
163,840
tokens
Compare vs GPT-4o
Developer ID: deepseek/deepseek-v3.2-exp

Related Models

deepseek
$0.45/1M

DeepSeek: R1 0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par wi...

📝 163,840 ctx Compare →
deepseek
$0.26/1M

DeepSeek: DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficienc...

📝 163,840 ctx Compare →
deepseek
$0.70/1M

DeepSeek: R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-...

📝 131,072 ctx Compare →