Deepseek V4 Flash 0731

Name: Deepseek V4 Flash 0731
Author: Novita AI

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

Context

1.0M

Max output

393K

Input price

$0.14/1M tokens

Output price

$0.28/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDdeepseek/deepseek-v4-flash-0731

ProviderNovita AI

CreatorDeepSeek

Familydeepseek

License—

Parameters—

Statusactive

Input modalitiestext, image

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date2026-08-01

Deprecation date—

Typechat

Reasoning tokens—

Max input—

Open weight—

Sourceofficial

Last updated2026-08-02

Tools

Function Callingfunction_calling

Call external functions and APIs

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input

$0.14

Output

$0.28

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Price across providers

Provider	Input	Output	Since launch
Vercel AI Gatewaycheapest	$0.01	$0.03	↓89%
OpenRouter	$0.09	$0.18	↓36%
Novita AI	$0.14	$0.28	—

Family Comparison: deepseek

Model	Caps	Perf	Speed	Context	Max out	Pricing
DeepSeek-OCR 2	RVTS	—	—	8K	8K	$0.03$0.03
DeepSeek-OCR	RVTS	—	—	8K	8K	$0.03$0.03
Deepseek V4 Flash 0731	RVTS	—	—	1.0M	393K	$0.14$0.28
Deepseek V4 Flash	RVTS	—	—	1.0M	393K	$0.14$0.28
Deepseek V3.2	RVTS	—	—	164K	66K	$0.27$0.4
DeepSeek V3 0324	RVTS	—	—	164K	66K	$0.27$1.12
Deepseek V3.1 Terminus	RVTS	—	—	131K	33K	$0.27$1
DeepSeek V3.1	RVTS	—	—	131K	33K	$0.27$1
Deepseek V3.2 Exp	RVTS	—	—	164K	66K	$0.27$0.41
DeepSeek V3 (Turbo)	RVTS	—	—	64K	16K	$0.4$1.3
Deepseek Prover V2 671B	RVTS	—	—	160K	160K	$0.7$2.5
DeepSeek V3	RVTS	—	—	64K	8K	$0.89$0.89
DeepSeek V3	RVTS	—	—	64K	16K	$0.89$0.89
Deepseek V4 Pro	RVTS	—	—	1.0M	393K	$1.6$3.2

API

GET/v1/models/novita/deepseek/deepseek-v4-flash-0731