1. What are rate limits
Rate limits are restrictions that our API imposes on the number of times a user or client can access our services within a specified period of time. The rate limits for MiniMax’s API are divided into two types: RPM and TPM.- RPM (Requests Per Minute): The maximum number of requests that can be sent per minute
- TPM (Tokens Per Minute): The maximum number of tokens (input + output) that can be processed per minute
2. Why do we have rate limits
Rate limits are a common practice for APIs and are implemented for several reasons:- Preventing abuse and misuse: Rate limits help protect the API from malicious or excessive usage. For example, they prevent users from overloading the API with excessive calls in an attempt to cause an overload or service disruption. By setting rate limits, such malicious activities can be avoided.
- Ensuring fair access: Rate limits ensure that everyone can access the API fairly. They prevent scenarios where one person or organization makes an excessive number of requests, potentially leading to unequal resource allocation for other users. By limiting the number of requests a single user can make, it ensures that the majority of users have the opportunity to access the API without experiencing performance slowdowns.
- Maintaining a consistent experience: By enforcing rate limits, MiniMax helps ensure a smooth and consistent experience for all users.
3. Rate limits for our API
The rate limits applied to your account depend on the model and interface you use. The specific rate limits are shown in the tables below :- The rate limits of Speech Generation
| API | Model | RPM | TPM |
|---|---|---|---|
| T2A | speech-2.5-turbo/hd speech-02-turbo/hd speech-01-turbo/hd | 60 | 20,000 |
| Voice Cloning | —— | 60 | —— |
| Voice Design | —— | 20 | —— |
- The rate limits of Video Generation
| API | Model | RPM |
|---|---|---|
| Video Generation | 02 Series: MiniMax-Hailuo-02 01 Series: T2V-01-Director、T2V-01、I2V-01-Director、 I2V-01、I2V-01-live、S2V-01 | 5 |
- The rate limits of Music Generation
| API | Model | RPM | CONN |
|---|---|---|---|
| Music Generation | Music-1.5 | 120 | 20 |
- The rate limits of Chat Completion
| API | Model | RPM | TPM |
|---|---|---|---|
| Chat Completion | MiniMax-M2 | 120 | 12,000,000 |
- The rate limits of Image Generation
| API | Model | RPM | TPM |
|---|---|---|---|
| Image Generation | image-01 | 10 | 60 |