Skip to content

❓ Frequently Asked Questions

What is quota? How is it calculated?

The quota calculation formula is as follows:

Quota = Group Multiplier * Model Multiplier * (Prompt Token Count + Completion Token Count * Completion Multiplier)

Completion Multiplier explanation:

  • GPT3.5: Fixed at 1.33
  • GPT4: Fixed at 2 (same as official)

Notes:

  • In non-streaming mode, the official API returns the total tokens consumed, but the multipliers for prompt and completion are different
  • ComputeVault's default multipliers are consistent with the official ones and have been adjusted accordingly
Why does it say 'insufficient quota' even though my account has enough?

This is because token quota and account quota are separate:

  • Token quota is only used to set the maximum usage limit
  • Users can freely set token quota
  • Please check if your token quota is sufficient