Skip to navigation

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

Back to model catalog
Zero data retention
Yes
Pricing (lowest)
$0.12/M / $0.42/M
Context
1M
Released
Aug 4, 2026

Vendors

Capabilities
Pareto$0.12$0.48$0.00241M384KOct 15, 2026
Baseten$0.30$1.20$0.031M384KSep 10, 2026
Fireworks AI$0.22$0.66$0.0071M384KSep 10, 2026
Novita AI$0.30$1.20$0.0061M384KSep 10, 2026
DeepInfra30% off$0.14$0.20$0.42$0.60$0.0042$0.0061M384KSep 9, 2026
DeepSeek$0.15$0.60$0.0031M384KSep 9, 2026
Luminal$0.135$0.54$0.00271M384KSep 9, 2026
Particle AI$0.15$0.60$0.0031M384KAug 4, 2026
Telnyx$0.30$1.20$0.0061M64KAug 4, 2026

Vendor details

BasetenDeepInfraDeepSeekFireworks AILuminalNovita AIParetoParticle AITelnyx
Promotion-DeepInfra promo 30%, 30% off-------
Peak hoursNot time-varyingNot time-varying01:00–04:00, 06:00–10:00 UTCNot time-varyingNot time-varyingNot time-varying01:00–04:00, 06:00–10:00 UTC04:00–20:30 America/New_YorkNot time-varying
Peak input cost$0.30/M$0.14/M$0.30/M$0.22/M$0.135/M$0.30/M$0.24/M$0.30/M$0.30/M
Peak output cost$1.20/M$0.42/M$1.20/M$0.66/M$0.54/M$1.20/M$0.96/M$1.20/M$1.20/M
Peak cache read cost$0.03/M$0.0042/M$0.006/M$0.007/M$0.0027/M$0.006/M$0.0048/M$0.006/M$0.006/M
CurrencyUSDUSDUSDUSDUSDUSDUSDUSDUSD
Availabilityavailableavailableavailableavailableavailableavailableavailableavailableavailable
Reasoning effort levels
noneminimallowmediumhighxhighmax
noneminimallowmediumhighxhighmax
noneminimallowmediumhighxhighmax
noneminimallowmediumhighxhighmax
noneminimallowmediumhighxhighmax
noneminimallowmediumhighxhighmax
noneminimallowmediumhighxhighmax
noneminimallowmediumhighxhighmax
-
Modalities
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextInput: ImageOutput: TextOutput: Tool use
Input: TextOutput: TextOutput: Tool use