DeepSeek V3.2
language modelDeepSeek
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...
Key facts
| Made by | DeepSeek |
|---|---|
| Type | language model |
| Released | September 29, 2025 |
| Reads at once | 163,840 tokens |
| Price (API, per million tokens) | $0.28 in · $0.42 out |
| Input → output | text → text |
Questions about DeepSeek V3.2
Who makes DeepSeek V3.2?
DeepSeek V3.2 is made by DeepSeek.
When was DeepSeek V3.2 released?
We first saw DeepSeek V3.2 listed on September 29, 2025.
How much does DeepSeek V3.2 cost?
Through OpenRouter it costs $0.28 per million input tokens and $0.42 per million output tokens. Prices change, so check the provider before you build on it.
How much text can DeepSeek V3.2 read at once?
Up to 163,840 tokens, roughly 122.9K words.
More from DeepSeek
DeepSeek-OCRDeepSeek · vision and multimodal model
Oct 17, 2025released
DeepSeek-R1DeepSeek · language model
Jan 20, 2025released
DeepSeek V3DeepSeek · language model
Dec 25, 2024released
DeepSeek-R1-Distill-QwenDeepSeek · language model
Jan 20, 2025released
DeepSeek V4.1 FlashDeepSeek · language model
Sep 10, 2026released
DeepSeek V4 Flash VisionDeepSeek · language model
Aug 21, 2026released
Other language models
gpt2Openai Community · language model
Mar 2, 2022released
Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
optMeta · language model
May 11, 2022released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Ollamaollama · language model
Jun 26, 2023released
pythiaEleutherAI · language model
Feb 8, 2023released
Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with DeepSeek.