DeepSeek V4 Flash (0731)

HOT

Fast general-purpose model with 1M context, re-post-trained by DeepSeek on 2026-07-31 for agentic and coding tasks. Supports extended thinking modes, JSON output, and function calling.

1M context·$0.44 in·$1.32 out·Apr 2026 release·Reasoning, Tools / functions

Available on

DeepSeek OpenRouter Alibaba Fireworks AI NVIDIA

Providers

Where DeepSeek V4 Flash (0731) runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutputCache read

DeepSeek

creator

deepseek-v4-flash

$0.44

$1.32

$0.01

OpenRouter

deepseek/deepseek-v4-flash

$0.09

$0.18

$0.02

Alibaba

deepseek-v4-flash

$0.20

$0.40

$0.04

Fireworks AI

delisted

accounts/fireworks/models/deepseek-v4-flash

$0.14

$0.28

$0.03

NVIDIA

delisted

deepseek-ai/deepseek-v4-flash

Free

Usage mix in Big-AGI: DeepSeek 99%Specs as reported by each service · usage over the last 2 days · refreshed hourly

Run DeepSeek V4 Flash (0731) in Big-AGI.

Connect your own key on any of the services above, at their rates, no markup - and run it side by side with every other model.

Launch Big-AGI

BIG-AGI

Product

Features Models Controls What's new BEAM Technology

Resources

Documentation Discord GitHub

Company

Email Us Privacy Terms