All models
DeepSeek
DeepSeek V4 Flash
DeepSeek's 284B mixture-of-experts Flash model: 1M context, fast, strong at coding, near-zero cost per message. Text only. Its successor DeepSeek V4.1 Flash costs the same, so move up unless you need this exact version.
OpenOpen-weight models with lighter filters. Discuss more, refuse less.
Smart & Cheap
Intelligence
~0.23 credits
Estimated price per message
1M tokens
Context window
Text
Reads
DeepSeek V4 Flash is a legacy model. Its successor, DeepSeek V4.1 Flash, is faster or cheaper - and chats that used DeepSeek V4 Flash 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
~0.23 credits≈ 434 messages for 1 €
Context window
1M tokens≈ 1,613 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 V4 Flash
Same facts, side by side.
Try DeepSeek V4 Flash now.
No subscription. Free credits to start. The chat opens with DeepSeek V4 Flash selected and a prompt ready - just send.