Rate limits
Rate limits govern how many requests you can make. The following limits apply to every account, regardless of account status.
Complimentary model limits
If you are using a complimentary model (with an ID ending in -free, or jev), the following limits apply:
Personal daily allowance
| Model ID | Requests per day |
|---|---|
deepseek-flash-free |
200 |
deepseek-v4-flash-free |
200 |
glm-5.3-flash-free |
200 |
jev |
Unlimited |
Personal allowances reset daily at 00:00 (UTC+8).
Platform-wide daily capacity
Complimentary models are billed at a 99% promotional discount as a limited daily offer: in addition to your personal allowance, the platform provides a limited total capacity for complimentary models each day, first come, first served.
| Complimentary lane | Daily capacity |
|---|---|
DeepSeek lane (shared by deepseek-flash-free and deepseek-v4-flash-free) |
~6 billion tokens |
GLM lane (glm-5.3-flash-free) |
~2 billion tokens |
TypeSafe lane (jev) |
Unlimited |
- Your personal allowance and the platform-wide capacity apply at the same time; reaching either pauses complimentary access for the rest of the day.
jevhas no personal daily allowance and does not count toward the platform-wide capacity; usage is unlimited.- During peak hours the daily capacity may run out early. It is not replenished within the same day and resets together with personal allowances at 00:00 (UTC+8), so off-peak usage is recommended.
- Any change to the daily capacity will be announced on this page in advance.
Once a complimentary allowance is exhausted, switch to the corresponding paid model: deepseek-flash, deepseek-v4-flash, or glm-5.3-flash. Paid models are not subject to the daily capacity.