reroute

DeepSeek: 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
In / Out Price
$0.30 / $1.20 per 1M
Context
1M
Released
Sep 10, 2026
Knowledge Cutoff
—

Pricing

What Reroute charges per unit. No markup on inference — you pay the carrier's price, metered from the carrier's own usage numbers.

Input tokens
$0.30 / M
Output tokens
$1.20 / M
Cache read
$0.006 / M

By provider

Each carrier sets its own price. The router weighs these against uptime when it picks one.

ProviderInput /MOutput /MCache read /MCache write /MDiscount
Relace$0.0168$0.80$0.008——
Baidu$0.0354$0.142$0.000708—88%
Morph$0.045$0.60$0.01——
Ionstream$0.05$1.15$0.006——
Wafer$0.055$1.20$0.044——
Sail Research$0.08$0.40$0.01——
Decart$0.09$0.18$0.018——
InferenceNet$0.105$0.60$0.015——
DekaLLM$0.12$1.20$0.005——
DeepInfra$0.14$0.42$0.0042—30%
StreamLake$0.15$0.60$0.003—50%
Alibaba$0.15$0.60$0.015——
DeepSeek$0.15$0.60$0.003——
GMICloud$0.18$0.72$0.0036—40%
Novita$0.195$0.78$0.0039—35%
CoreWeave$0.20$0.65$0.03——
Phala$0.21$0.84$0.0042—30%
DigitalOcean$0.225$0.90$0.006——
Makora$0.27$1.15$0.009——
Crusoe$0.29$1.20$0.007——
AtlasCloud$0.30$1.20$0.03——
BaseTen$0.30$1.20$0.007——
Together$0.30$1.20$0.006——
SiliconFlow$0.30$1.20$0.006——
Modal$0.30$1.20$0.03——
BaseTen$0.30$1.20$0.007——
Parasail$0.30$1.20$0.006——
Fireworks$0.30$1.20$0.006——
Venice$0.30$1.20$0.0075——
Fireworks$0.45$1.80$0.009——