Ollama admits misbilling on deepseek-v4.1-flash, resets usage for affected users

ollama · x · 2026-09-22

Ollama announced that for several hours some requests to the deepseek-v4.1-flash model were charged at an incorrect rate, causing higher-than-expected usage consumption. The company apologized and remedied it: affected users' usage (monthly, or weekly plus session on legacy plans) has been reset, and any extra usage consumed via this model has been restored to their accounts.

Original post →

More from Models

Models channel →