All models
DeepSeek
DeepSeek V3.2
DeepSeek's late-2025 open-weight model with sparse attention that makes long-context work cheaper. A 671B mixture-of-experts, good at coding and analysis for very little money, text only. DeepSeek V4.1 Flash is newer and costs even less.
OpenOpen-weight models with lighter filters. Discuss more, refuse less.
Smart & Cheap
Intelligence
~0.62 credits
Estimated price per message
164K tokens
Context window
Text
Reads
DeepSeek V3.2 is a legacy model. Its successor, DeepSeek V4.1 Flash, is faster or cheaper - and chats that used DeepSeek V3.2 move to it automatically.
See DeepSeek V4.1 FlashThe facts
Made by
DeepSeek
Content tier
OpenOpen-weight models with lighter filters. Discuss more, refuse less.
Intelligence
Smart & Cheap
Estimated price per message
~0.62 credits≈ 161 messages for $1
Context window
164K tokens≈ 252 pages of text in one go
Reads
Text
Writes
Text
Tool use
Yes - search, memory, code and more
Served via
OpenRouter, Unbottled AI
Status
Legacy
A typical message: 16K tokens in, 1.5K out. Short replies cost less. Models served via OpenRouter bill the real provider cost plus our markup, so actual charges vary. 1 credit = $0.01.
Compare DeepSeek V3.2
Same facts, side by side.
Try DeepSeek V3.2 now.
No subscription. Free credits to start. The chat opens with DeepSeek V3.2 selected and a prompt ready - just send.