DeepSeek

DeepSeek V4 Flash 0423: price, context window and ranking

As of 18 October 2026, DeepSeek V4 Flash 0423 from DeepSeek costs $0.091 per million input tokens and $0.182 per million output tokens on OpenRouter, with a context window of 1.05M tokens. On the LMArena text leaderboard it ranks 92 with a score of 1,431.8. It is number 14 on OpenRouter by usage, with 1.8% of tokens in the past 7 days.

Oesnada automated editorial system · Last updated: (2026-10-18)

Input price
$0.091

per 1M tokens

Output price
$0.182

per 1M tokens

Context window
1.05M

tokens

LMArena score
1,431.8

rank 92

Usage share, 7 days
1.8%

rank 14

Providers
16

uptime 99.1%

Specifications

Specifications
FieldValue
ProviderDeepSeek
Input price per 1M tokens$0.091
Output price per 1M tokens$0.182
Blended price per 1M tokens (3:1)$0.1138
Context window1,048,576
Providers serving it16
Average uptime, past day99.1%
LMArena1,431.8 (rank 92)
Arena score per dollar12,587.3
Usage share, 7 days1.8% (rank 14)
Added to OpenRouter2026-04-24
Modalitytext->text
OpenRouter model IDdeepseek/deepseek-v4-flash

Price history

DeepSeek V4 Flash 0423: Price historyInput and output price per million tokens, one point per daily snapshot.$0.0864$0.1198$0.1532$0.18652026-10-162026-10-172026-10-18
  • Input
  • Output
DeepSeek V4 Flash 0423: Price history
DateInputOutput
2026-10-16$0.091$0.182
2026-10-17$0.091$0.182
2026-10-18$0.091$0.182

Usage rank history

DeepSeek V4 Flash 0423: Usage rank historyRank by OpenRouter token usage over the previous 7 days; lower is better.131314142026-10-162026-10-172026-10-18
  • Usage rank
DeepSeek V4 Flash 0423: Usage rank history
DateUsage rank
2026-10-1613
2026-10-1714
2026-10-1814

Compare with other models

Frequently asked questions

How much does DeepSeek V4 Flash 0423 cost per million tokens?

DeepSeek V4 Flash 0423 costs $0.091 per million input tokens and $0.182 per million output tokens on OpenRouter, as of 18 October 2026. At a mix of three parts input to one part output the blended price is $0.1138 per million tokens.

What is the context window of DeepSeek V4 Flash 0423?

DeepSeek V4 Flash 0423 has a context window of 1.05M tokens (1,048,576 exactly).

How does DeepSeek V4 Flash 0423 rank on LMArena?

DeepSeek V4 Flash 0423 is ranked 92 on the LMArena text leaderboard with a score of 1,431.8 from 51,987 votes. The listing used is "deepseek-v4-flash".

When was DeepSeek V4 Flash 0423 released?

OpenRouter lists DeepSeek V4 Flash 0423 as added on 24 April 2026.

Who provides DeepSeek V4 Flash 0423?

DeepSeek V4 Flash 0423 is served by 16 providers on OpenRouter, with average uptime of 99.1% over the past day.

Methodology and sources

The catalogue, prices, context lengths and provider counts come from OpenRouter's public Models API. They are fetched every day at 06:00 Istanbul time and stored as a daily snapshot. Weekly changes are calculated by Oesnada by comparing those snapshots; there is no data before 16 October 2026.

Usage shares are calculated from the daily token totals of OpenRouter's Data API: a model's tokens over the past 7 days divided by all tokens in the same period, including the aggregated long tail outside the top 50. Token counts come from each provider's own tokenizer and are not directly comparable across providers. The data is published by OpenRouter under CC BY 4.0. Variants such as ":free" are counted separately, so shares here can differ from OpenRouter's own ranking page.

Quality rankings come from LMArena's text (overall) leaderboard. A model is matched only when its name matches exactly; if a model has several listings, the highest-scoring one is used. "Frontier" means a model in the LMArena top 15.

"Best value" divides the LMArena score by the blended price (three parts input to one part output). Arena scores are not a linear scale, so the ratio is a rough guide. This page is produced automatically.

Related Oesnada stories: DeepSeek

  1. Study: Chinese AI Labs Included Developer Safety Results in Just 3.6% of

    The dataset tracked releases from nine prominent labs, spanning tech giants ByteDance, Alibaba, Tencent, and Baidu alongside startups such as DeepSeek, Moonshot, Zhipu, MiniMax, and StepFun.

    Importance 94/100
  2. Hacker Targeting South Korean Banks Used LLMs and ARTEX Tool, Analysis Finds

    Investigators discovered open directories containing Claude Code session histories, configuration files, and memory logs, which revealed that the perpetrator relied on ARTEX—an open-source Chinese tool designed for autonomous penetration testing, or simulated cyberattacks used to uncover system weaknesses—paired with large language models.

    Importance 94/100

All AI models

AI Models

Download the data

Cite this page

Oesnada, "DeepSeek V4 Flash 0423: price, context window and ranking", https://oesnada.com/ai-models/deepseek-deepseek-v4-flash, accessed 18 October 2026.