anonrouter
Sign up
DeepSeek

DeepSeek V4.1 Flash

deepseek
Chat

DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.

Modalities

In / out price

$0.23 / $0.69per 1M

Cached price

$0.0069per 1M

Context

1M

Max output

131K

Providers

7 routes

Compare providers by price, privacy, and speed.

Tinfoil
TEE$0.72$1.75$0.0121M33K——
VeniceVenice
Private$0.35$1.40$0.00871M262K——
DeepInfraDeepInfra
Private$0.23$0.69$0.00691M131K——
Baseten
Private$0.35$1.40$0.00811M131K——
Wafer
Private$0.22$0.75$0.00691M131K——
NEAR AI
Anonymous$0.32$1.25$0.00631M393K——
Cheaper Inference
Anonymous$0.17$0.68$0.00341M131K——

Privacy

3 / 4

Hardware-isolated routing

TEE tier

  1. Anonymous
  2. Private
  3. TEE
  4. E2EE

Inference runs inside a hardware-isolated, attestable environment. TEE protects processing, but does not by itself mean the client encrypted the request end to end. Learn more

Features

6
Streaming
Tool calling
Vision
Reasoning
Code optimized
Confidential compute

Uptime

FAQ

Common questions about DeepSeek V4.1 Flash.