DeepSeek V4 Flash 0731

DeepSeek · deepseek/deepseek-v4-flash-0731

← Back to leaderboard

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

DeepSeek V4 Flash 0731 ranks #10 of 359 models in the default AI Benchmark Hub order (quality first, then cost). At $0.06 blended per million tokens, it is cheaper than 95% of models with published API pricing. Its 1,048,576-token context window is 4.0× the catalog median (262,144 tokens). A quality index of 86.1 places it at #9 of 35 models with an Arena Elo signal.

open weightstexttext->text

Context

Max context: 1048576
Max output: 943718

Pricing

Input / 1M: 0.04
Output / 1M: 0.08
Blend / 1M: 0.06

Quality

Quality index: 86.1

Provider

Provider: DeepSeek
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.06per 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$0.06
10,000,000$0.60
100,000,000$6.00

Related models

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

More from DeepSeek

Closest API price

Closest quality index