Vibeleaderboard
← All Intel
Intel / article

Model pricing is getting more complex over time.

Source
openrouter.ai
Author
OpenRouter
Date

Context

The same amount of AI processing can cost different amounts depending on when it runs. DeepSeek's published Flash and V4 Pro pricing schedule makes off-peak rates half the peak rates. Peak periods run from 01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays, excluding Chinese public holidays; weekends and those holidays are entirely off-peak. For work whose timing is flexible, the schedule therefore matters alongside the amount of text processed. These are the rates and timing rules in the published pricing documentation, rather than a permanent price attached to a model name.

Read the source openrouter.ai
More from OpenRouter
Recommended reads
Comments

Checking sign-in…

Loading comments…