← LLM Models

DeepSeek V3.2

DeepSeek

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Official page →
📖Context131K tokens
🚀Speed-
💵Input price$0.269/1M
💸Output price$0.400/1M

Made by

🏢
DeepSeek
provider
→

More from DeepSeek

DeepSeek R1OSS
Score 75$0.700/1M→
DeepSeek V3OSS
Score 68$0.257/1M→
R1 Distill Llama 70BOSS
$0.800/1M→
R1 0528
$0.500/1M→
R1 Distill Qwen 32BOSS
$0.290/1M→
DeepSeek V3.1
$0.250/1M→

API Providers

OpenRouter
Input
$0.269/1M
Output
$0.400/1M
→

Details

Provider
DeepSeek
Parameters
-
Context
131K tokens
Speed
-
Open Source
No
License
Proprietary
Released
Dec 2025

Reviews

No reviews yet

Log in to rate

← View all 409 models