SmophyAI

Published daily · Next update 02:00 UTC

DeepSeek · DeepSeek family

DeepSeek: DeepSeek V4 Flash 0423

DeepSeek: DeepSeek V4 Flash 0423 ranks #28 of 94 models by Artificial Analysis quality score (34.3) at $0.19/1M tokens blended - and ranks #2 of 353 by average real OpenRouter usage share over the trailing 80-day window (14.37%). Available from 24 providers at up to 100.0% uptime.

  1. Quality (Intelligence Index) - 34.3
  2. Coding index - 69.1
  3. Agentic index - 41
  4. Price (blended $/1M) - 0.19
  5. Context window - 1,310,720
  6. Usage rank - #2 of 353
  7. Providers - 24
  8. Open/closed - open
Provider reliability →Compare DeepSeek versions →

Usage share over time

24.64%18.48%12.32%6.16%0.00%Share of usageJul 5Aug 13Sep 22

What DeepSeek: DeepSeek V4 Flash 0423 is actually used for

Share of each real task category's classified traffic this model handles, from OpenRouter's task classification.

TaskShare of task traffic
Roleplay & Fiction32.0%
Content Writing30.7%
Memory Extraction25.9%
Math25.0%
Conversation24.9%
Data Transformation23.9%
Q&A & Knowledge22.2%
Summarization18.9%

Compare DeepSeek: DeepSeek V4 Flash 0423

vs Ox Alpha →vs DeepSeek: DeepSeek V4.1 Flash (batch) →vs Z.ai: GLM 5.3 Flash (batch) →vs Xiaomi: MiMo-V2.5 →vs Tencent: Hy3 →vs OpenAI: GPT-5.6 Luna (batch) →vs Tencent: Hy3 preview →vs Union Alpha →vs inclusionAI: Ling 3.0 Flash →

Frequently asked questions

What is DeepSeek: DeepSeek V4 Flash 0423's quality score?

DeepSeek: DeepSeek V4 Flash 0423 scores 34.3 on Artificial Analysis's Intelligence Index, ranking #28 of 94 models with a published score.

How much does DeepSeek: DeepSeek V4 Flash 0423 cost?

DeepSeek: DeepSeek V4 Flash 0423 costs $0.19 per 1M tokens (blended 75% prompt / 25% completion pricing).

Is DeepSeek: DeepSeek V4 Flash 0423 widely used?

DeepSeek: DeepSeek V4 Flash 0423 ranks #2 of 353 models by average real OpenRouter usage share, averaging 14.37% of classified token volume over the trailing 80-day window.

Is DeepSeek: DeepSeek V4 Flash 0423 open-weight or closed?

DeepSeek: DeepSeek V4 Flash 0423 is an open-weight model.

Source: OpenRouter (openrouter.ai/rankings), as of September 23, 2026.

Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).

Methodology: www.smophy.ai/benchmark/methodology

Token counts originate from each provider's own tokenizer and are not directly comparable across providers.