Skip to content
llmprice

DeepSeek V4.1 Flash

Updated Sep 11, 2026

deepseek-flash1.1M context393k max outputreleased Sep 10, 2026Open weightsReasoningTool calling
Cheapest input
$0.15
Cheapest output
$0.6
Official (DeepSeek)
$0.6
output per 1M tokens
Providers
24
offering this model
Spread
2.5×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContextChanged
DeepSeekopenCheapest$0.15Cheapest$0.6$0.0031.0M
DevPass (LLM Gateway)open$0.15$0.6$0.0031.1M
LLM Gatewayopen$0.15$0.6$0.0031.1M
Merge Gatewayopen$0.15$0.6$0.0031.0M
NanoGPTopen$0.15$0.6$0.0031.0M
OpenCode Goopen$0.15$0.6$0.0031.0M
OpenRouteropen$0.15$0.6$0.0031.0M
AIHubMixopen$0.155$0.62$0.00311.0M
Deep Infraopen$0.2$0.6$0.0061.0Mtodayout −50%
Eden AIopen$0.2$0.6$0.0061.0Mtodayout −50%
Fireworks AIopen$0.22$0.66$0.0071.0M
Requestyopen$0.22$0.66$0.0071.0Mtodayout −45%
CrossModelopen$0.27$1.08$0.0054$0.271.0M
GreenPTopen$0.2556$1.2778$0.01281.0M
Basetenopen$0.3$1.2$0.031.0M
Hugging Faceopen$0.3$1.21.0M
Charm Hyperopen$0.3$1.2$0.031.0M
Kilo Gatewayopen$0.3$1.2$0.0061.0M
Ofoxopen$0.3$1.2$0.0061.0M
Vercel AI Gatewayopen$0.3$1.2$0.0061.0M
Venice AIopen$0.375$1.5$0.00751.0M
NaNfreefreefree1.0M

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

Provider1M input1M outputContext
ClinePassplan$0.15$0.61.0M

Other deepseek-flash models