deepseek-v4-flash-vision-exp

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

deprecatedmit

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

Context

Max output

384K

Input price

$0.22/1M tokens

Output price

$0.65/1M tokens

Capabilities

Show unsupported (3)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

JSON Mode

Infrastructure

Streaming

Fine-tuning

Details

Model IDdeepseek/deepseek-v4-flash-vision-exp

ProviderVercel AI Gateway

CreatorDeepSeek

Familydeepseek

Licensemit

Statusdeprecated

Typechat

Input modalitiestext, image

Output modalitiestext

Open weightYes

Parameters—

Architecture—

Context window1M tokens

Max input—

Max output384K tokens

Reasoning tokensYes

Knowledge cutoff—

Release date—

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.22

Output

$0.65

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: deepseek

Model	Caps	Perf	Speed	Context	Max out	Pricing
deepseek-v4-flash-0731	RTS	—	—	1M	—	$0.04$0.15
deepseek-v4.1-flash-1017	RTS	—	—	1M	—	$0.04$0.29
deepseek-v4.1-flash	RTS	—	—	1M	—	$0.04$0.3
deepseek-v4-flash	RTJMSF	—	—	1M	384K	$0.06$0.18
deepseek-v4-flash-vision-exp	RTJMSF	—	—	1M	384K	$0.22$0.65
deepseek-v4.1-flash-beta	RTS	—	—	1M	—	$0.22$0.66
deepseek-v3.1	RTS	—	—	164K	—	$0.25$0.95
deepseek-v3.2-thinking	RTS	—	—	164K	—	$0.26$0.38
deepseek-v3.2	RTS	—	—	164K	—	$0.26$0.38
deepseek-v3.1-terminus	RTS	—	—	131K	—	$0.27$1
deepseek-v3	TS	—	—	164K	—	$0.27$1.12
deepseek-v4.1-flash-1017-fast	RTS	—	—	1M	—	$0.6$2.4
deepseek-v4.1-flash-fast	RTS	—	—	1M	—	$0.6$2.4
deepseek-v4-pro-0813	RTS	—	—	1M	—	$0.66$1.98
deepseek-v4-pro	RTJMSF	—	—	1M	384K	$0.66$1.98

API

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