DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Modalities
Text
Image
In / Out price
$0.15 / $0.60 per 1M
Context
1.05M · 384K out
Released
Sep 10, 2026

Providers

Live list prices and uptime across 22 providers serving this model.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
Morph$0.12$0.48$0.0041.05M944K98.43%
Relacefp4$0.13$0.52$0.011.05M944K99.70%
DeepInfrafp8$0.14$0.42$0.0041.05M131K99.79%
Alibaba$0.15$0.60$0.0151M393K99.90%
DeepSeek$0.15$0.60$0.0031.05M384K100.00%
Sail Researchfp4$0.20$0.60$0.041.05M384K99.96%
Wafer$0.20$0.60$0.0061.05M944K99.83%
StreamLakefp8$0.22$0.879$0.0041.02M384K99.14%
Fireworks$0.22$0.66$0.0071.05M944K99.90%
Phala$0.276$1.104$0.0061.05M393K99.12%
GMICloudfp8$0.285$1.14$0.0061.05M944K99.35%
Novitafp8$0.285$1.14$0.0061.05M393K99.99%
AtlasCloudfp8$0.30$1.20$0.031.05M393K99.11%
BaseTenfp8$0.30$1.20$0.031.05M33K98.15%
Makora$0.30$1.20$0.0061.05M393K98.75%
DigitalOcean$0.30$1.20$0.0061.05M944K99.02%
Together$0.30$1.20$0.0061.05M944K99.89%
SiliconFlowfp8$0.30$1.20$0.0061.05M393K99.44%
Modal$0.30$1.20$0.031.05M944K99.95%
BaseTenfp8$0.30$1.20$0.031.05M33K98.20%
Parasailfp8$0.30$1.20$0.0061.05M944K91.74%
Venicefp8$0.375$1.50$0.0071M131K99.22%

Implicit prompt caching available — repeated context bills at the cache read rate.

Capabilities

Tool calling
Reasoning
Frequency penalty
Include reasoning
Logit bias
Logprobs
Max tokens
Min p
Presence penalty
Reasoning effort
Repetition penalty
Response format
Seed
Stop
Structured outputs
Temperature
Tool choice
Top K
Top logprobs
Top P

Pricing detail

Input
$0.15
Output
$0.60
Cache read
$0.003
Cache write

USD per 1M tokens.