DeepSeek V4 Flash 0423

DeepSeek · deepseek/deepseek-v4-flash

← Back to leaderboard

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

DeepSeek V4 Flash 0423 ranks #10 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.13 blended per million tokens, it is cheaper than 89% of models with published API pricing. Its 1,024,000-token context window is 3.9× the catalog median (262,144 tokens). A quality index of 86.3 places it at #9 of 41 models with an Arena Elo signal.

open weightstexttext->text

Context

Max context: 1024000
Max output: 384000

Pricing

Input / 1M: 0.09
Output / 1M: 0.18
Blend / 1M: 0.13

Quality

Quality index: 86.3

Provider

Provider: DeepSeek
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.13per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.13
10,000,000$1.33
100,000,000$13.29

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from DeepSeek

Closest API price

Closest quality index