DeepSeek-V4-Flash-Vision-Exp

Name: DeepSeek-V4-Flash-Vision-Exp
Author: DeepInfra

deepseek

DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and supports image input with visual grounding, tool calling, structured/JSON output, and configurable reasoning effort (low/high/max, or disabled).

Context

1.0M

Max output

384K

Input price

$0.44/1M tokens

Output price

$1.32/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp

ProviderDeepInfra

CreatorDeepSeek

Family—

Licensedeepseek

Parameters—

Statusactive

Input modalitiestext, image

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date—

Deprecation date—

Typechat

Reasoning tokensYes

Max input—

Open weightYes

Sourceofficial

Last updated2026-09-10

Tools

Function Callingfunction_calling

Call external functions and APIs

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input

$0.44

Output

$1.32

Cache write

—

Cache read

$0.01

↓90%$0.14

Batch in

—

Batch out

—

Price history · $/1M cache read

$0.14

$0.014

Sep 3Sep 10

Date	Input	Output	Cache read	Change
Sep 3, 2026	$0.44	$1.32	$0.14	—
Sep 10, 20268e0a0b7	$0.44	$1.32	$0.014	↓90%

Cache read is ↓90% since Sep 3, 2026, from $0.14 to $0.014 per 1M tokens.

Price across providers

Provider	Input	Output	Since launch
DeepInfracheapest	$0.44	$1.32	—
Fireworks AI	$1	$1	↑355%

API

GET/v1/models/deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp