All models
Head to head
DeepSeek V4.1 Flash vs DeepSeek V3.1
Price, context, inputs and filters. No benchmarks theatre.
DeepSeek V4.1 Flash costs 3.7× less per message.
DeepSeek V4.1 Flash holds 6.4× more context.
Fact
Made by
DeepSeek
DeepSeek
Content tier
Open
Open
Intelligence
Smart & Cheap
Smart & Cheap
Estimated price per message
~0.19 credits≈ 526 messages for $1
~0.71 credits≈ 140 messages for $1
Context window
1M tokens≈ 1,613 pages of text in one go
164K tokens≈ 252 pages of text in one go
Reads
Text, Images
Text
Writes
Text
Text
Tool use
Yes - search, memory, code and more
Yes - search, memory, code and more
Served via
OpenRouter, Unbottled AI
OpenRouter, Unbottled AI
Status
Current
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.