DeepSeek-V4-Flash
Model at DeepSeek
The basics
As of Nov 1- Status
- Price
- Context
- Open weights
- Speed
Updates
Role
Open-weight model at DeepSeek
Sep 2026 to now · 2 months
Apr 2026 to Sep 2026 · 5 months
Works with
From recorded changes
API · 2 shared changes
Similar models
DeepSeek's smallest model in its new architecture family, a 552B-parameter MoE with native visual understanding.
$0.15 in, $0.60 out
$1.32 in, $3.96 out
Cost vs peers
Tied for cheapest of 3 similar models by output price.
Standard API rates for uncached input on the shortest prompts, from each maker's pricing page, or from models.dev for models not researched here yet. DeepSeek-V4-Pro: Peak hours. Off-peak prices are half.
Where it works
Prices and uptime are OpenRouter's figures for each provider's cheapest endpoint. Uptime covers the last 24 hours.
Benchmarks
Higher is better. Green is DeepSeek-V4-Flash. Dark marks are similar models.
Independent
What people say
Reviews
Writing habits
Creative writing · EQ-Bench, among 51 models tracked here
Slop score
20.9
Overused AI words and phrases. Less slop than 30% of tracked models.
Repetition
4.3
Repeated words and ideas. Less repetition than 28% of tracked models.
Story length
6,031
Average characters per story. Longer than 34% of tracked models.