deepseek-v4-flash

Name: deepseek-v4-flash
Author: Vercel AI Gateway

mit

DeepSeek-V4-Flash hybrid model with both non-thinking and thinking (default) modes.

Context

Max output

384K

Input price

$0.01/1M tokens

Output price

$0.03/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDdeepseek/deepseek-v4-flash

ProviderVercel AI Gateway

CreatorDeepSeek

Familydeepseek

Licensemit

Parameters—

Statusactive

Input modalitiestext

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date2026-07-31

Deprecation date—

Typechat

Reasoning tokensYes

Max input—

Open weightYes

Sourceofficial

Last updated2026-08-05

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.01

↓89%$0.09

Output

$0.03

↓83%$0.18

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Price history · $/1M input

$0.14

$0.09

$0.01

Apr 25Jul 17Aug 5

Date	Input	Output	Change
Apr 25, 2026	$0.14	$0.28	—
Jul 17, 202620c73ac	$0.09	$0.18	↓36%
Aug 5, 202619c9fe3	$0.01	$0.03	↓89%

Input is ↓93% since Apr 25, 2026, from $0.14 to $0.01 per 1M tokens.

Price across providers

Provider	Input	Output	Since launch
Vercel AI Gatewaycheapest	$0.01	$0.03	↓93%
Novita AI	$0.14	$0.28	—
OpenRouter	$0.14	$0.28	—

Family Comparison: deepseek

Model	Caps	Perf	Speed	Context	Max out	Pricing
deepseek-v4-flash-0731	RVTS	—	—	1M	—	$0.01$0.03
deepseek-v4-flash	RVTS	—	—	1M	384K	$0.01$0.03
deepseek-v3.1	RVTS	—	—	164K	—	$0.25$0.95
deepseek-v3.2-thinking	RVTS	—	—	164K	—	$0.26$0.38
deepseek-v3.1-terminus	RVTS	—	—	131K	—	$0.27$1
deepseek-v3	RVTS	—	—	164K	—	$0.27$1.12
deepseek-v3.2	RVTS	—	—	164K	—	$0.28$0.42
deepseek-v4-pro	RVTS	—	—	1M	384K	$0.43$0.87

API

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