LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

DeepSeek V4 Flash (Speed)

deepseek·deepseek/deepseek-v4-flash-speed·GA·Open weights·deepseek-flash series·NEW
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Specs & pricing

Input / output per 1M tokens
Reference price·Neuralwatt
$0.14 / $0.28
Blended $0.18 · Cache read $0.028
Lowest paid·NeuralwattGateway
$0.14 / $0.28
Blended $0.18
Context
1,048,560
Output limit
393,216
Knowledge cutoff
2025-05
Released / updated
2026-07-31 / 2026-07-31
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NeuralwattGateway$0.14$0.28$0.028—1,048,560393,216

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = higheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 1 of 1 providers.

Your usage cost

1Neuralwatt$28.56
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list $0.14Output list $0.28Min blended $0.18

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-22). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

DeepSeek Flash Latestsame series$0.003 / $2.40DeepSeek V4.1 Flashsame series$0.15 / $0.60deepseek-ai/DeepSeek-V4.1-Flash-Fastsame series$0.60 / $2.40Qwen3.7 Flashcheaper alternative$0.03 / $0.13Laguna S 2.1cheaper alternative$0 / $0Qwen Turbocheaper alternative$0.05 / $0.20Nemotron 3 Ultra (free)cheaper alternative$0 / $0
Data partly from models.dev (MIT) · Neuralwatt official docs ↗