Skip to content
Custom Comparison

Compare 2 AI Models

DeepSeek V4.1-Flash vs DeepSeek V4-Flash

DeepSeek V4.1-FlashDeepSeek
DeepSeek V4-FlashDeepSeek

Up to 3 models. Every selection is in the address bar, so the comparison is a link you can send.

Interactive Comparison

Loading chart...
$0.30 / $1.20 per million tokens
$0.15 / $0.60 per million tokens
Identity
DeveloperDeepSeekDeepSeek
ReleasedSep 2026Jul 2026
Retired—10 September 2026
StatusGARetired. DeepSeek retired V4-Flash on 2026-09-10; requests to deepseek-v4-flash are now served by DeepSeek V4.1-Flash, which has its own page. The figures below are V4.1-Flash's (off-peak), recorded here before that page existed.
LicenceMITProprietary
Self-hostableYes - open weights on Hugging FaceNo
Cost
Blended $/1M tokensinput × 0.75 + output × 0.25$0.525 / 1M tokens$0.262 / 1M tokens
Input price$0.300 / 1M tokens$0.150 / 1M tokens
Output price$1.200 / 1M tokens$0.600 / 1M tokens
Cached input$0.006 / 1M tokens (peak); $0.003 off-peak$0.014 / 1M tokens (peak); $0.007 off-peak
Batch discountOff-peak billing: 50% off all ratesOff-peak billing: 50% off all rates outside 01:00-04:00 and 06:00-10:00 UTC
Free tier—Not offered
Capacity
Context window1M tokens1M tokens
Max output384k tokens384k tokens
Long-context surchargeNone (flat rate across the 1M window)None — flat rate across the 1M window
Capability
Vision inYesNo
Audio inNoNo
Function callingYesYes
Structured outputYes - JSON outputYes — JSON output
Extended reasoningYes - thinking (default) and non-thinking modesYes — thinking (default) and non-thinking modes
Web searchNoNo
Code executionNoNo
Access
APIYesYes
Chat appYesYes
Cloud marketplacesNot offeredNot offered
Fine-tuningNot offered (weights are open)Not offered
Measured quality
LMArena Elo1475 (checked Oct 2026)1436 (checked Oct 2026)
LMArena rankRank 39Rank 103
Elo per dollarLMArena Elo ÷ blended $/1M tokens28105470