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
$0.375 / $1.50
per 1M
Cached price
$0.0075
per 1M
Context
1M
Max output
131K
Released
Sep 10, 2026
Providers
0 routesThe same model can have different pricing and privacy guarantees depending on who serves it. Only routes currently callable through AnonRouter are shown.
No provider route for this model is live right now.
Privacy
0 / 4No live route
AnonRouter is not currently offering a callable provider route for this model.
Features
8Streaming
Tool calling
Reasoning
Vision
JSON/schema
Web search
Code optimized
Prompt caching