DeepSeek: DeepSeek V4 Flash

Name: DeepSeek: DeepSeek V4 Flash
Author: OpenRouter

mit

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.

Context

1.0M

Max output

131K

Input price

$0.13/1M tokens

Output price

$0.25/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDdeepseek/deepseek-v4-flash

ProviderOpenRouter

CreatorDeepSeek

Familydeepseek

Licensemit

Parameters—

Status—

Input modalitiestext

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date2026-04-24

Deprecation date—

Typechat

Reasoning tokens—

Max input—

Open weightYes

Sourceofficial

Last updated2026-05-14

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.13

Output

$0.25

Cache write

—

Cache read

$0.03

Batch in

—

Batch out

—

Family Comparison: deepseek

Model	Caps	Perf	Speed	Context	Max out	Pricing
DeepSeek: DeepSeek V4 Flash (free)	RVTS	—	—	256K	256K
DeepSeek: DeepSeek V4 Flash	RVTS	—	—	1.0M	131K	$0.13$0.25
Nex AGI: DeepSeek V3.1 Nex N1	RVTS	—	—	131K	164K	$0.14$0.5
DeepSeek: DeepSeek V3.2	RVTS	—	—	131K	66K	$0.25$0.38
DeepSeek: DeepSeek V3.1 Terminus	RVTS	—	—	164K	33K	$0.27$0.95
DeepSeek: DeepSeek V3.2 Exp	RVTS	—	—	164K	66K	$0.27$0.41
DeepSeek: DeepSeek V3.2 Speciale	RVTS	—	—	164K	164K	$0.29$0.43
DeepSeek: DeepSeek V4 Pro	RVTS	—	—	1.0M	384K	$0.44$0.87

API

GET/v1/models/openrouter/deepseek/deepseek-v4-flash