The concurrency limit (concurrent requests running in parallel) depends on the tier you are on. Below are the current rates at the time of writing this, but please note that we will likely revisit them in the future.
| Plan | Flash and Turbo models | All other models |
|
Free |
4 | 2 |
| Starter | 6 | 3 |
| Creator | 10 | 5 |
| Pro | 20 | 10 |
| Scale | 30 | 15 |
| Business | 30 | 15 |
If you require a higher number of concurrent requests, please reach out to our Enterprise Department directly via this webpage. We will be happy to discuss a tailor-made plan that meets your specific requirements.
Conversational AI and Speech to Text have different concurrency limits: