Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

DeepSeek V4 Flash Latest

DeepSeek· released 1 Aug 2026

~deepseek/deepseek-v4-flash-latest
Input / 1M tokens
$0.009
Output / 1M tokens
$0.808
Context window1M tokens

Longest answer: 944K tokens

reads texttool callingreasoning
See it on openrouter.ai

About

DeepSeek V4 Flash Latest is a text model from DeepSeek whose identifier resolves to the latest model in the DeepSeek V4 Flash family. That redirecting behavior means the specific model behind the name can change as the family’s latest model changes. It accepts text, supports tools and reasoning, and produces text. Its context window is 1,048,576 tokens, with a maximum output of 943,718 tokens. Input costs $0.0086 per 1M tokens, and output costs $0.8084 per 1M tokens. Its model ID is ~deepseek/deepseek-v4-flash-latest, and its family is ~deepseek. DeepSeek released it on 2026-08-01. Teams considering it should account for both its large listed context and output limit and the fact that the name routes to the family’s latest model rather than a fixed member.

Who it is for

It suits text-based applications that need tool use, reasoning, or a large context and output allowance. Teams that need the model name to refer to a fixed family member should account for its latest-model redirect.

What is good

  • 1,048,576-token context window.
  • Maximum output of 943,718 tokens.
  • Supports tool use and reasoning.
  • Input costs $0.0086 per 1M tokens.

What to know first

  • Redirects to the latest V4 Flash family model.
  • Output costs $0.8084 per 1M tokens.
  • Accepts text input only.

Verdict

DeepSeek V4 Flash Latest offers a large context and output limit, with text input and tool support. Its redirect to the family’s latest model is important for teams that need a fixed model target.

Details

Lab
DeepSeekopenrouter.ai · 3 Oct 2026
Context
1,049Kopenrouter.ai · 3 Oct 2026
Input price
$0.009 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.808 / 1Mopenrouter.ai · 3 Oct 2026
Max output
943,718 tokensopenrouter.ai · 3 Oct 2026
Inputs
textopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources