Pay as You Go / Growth

Limits to consider if you use the Pay as You Go or Growth plans with Deepgram.

Speech to Text

If multiple services are used in one API call (e.g Speech to Text + Sentiment Analysis), the lower of the rate limits is applied.

Model	Service Limit
Nova-2	`Pre-Recorded`Up to 100 concurrent requests `Streaming` Up to 100 concurrent requests
Nova	`Pre-Recorded`Up to 100 concurrent requests `Streaming` Up to 100 concurrent requests
Enhanced	`Pre-Recorded`Up to 100 concurrent requests `Streaming` Up to 100 concurrent requests
Base	`Pre-Recorded`Up to 100 concurrent requests `Streaming` Up to 100 concurrent requests
Whisper Cloud	`Pre-Recorded` Up to 5 concurrent requests

Text to Speech REST

Model	Service Limit	Feedback
Aura	Pay as You Go: Up to 480 requests / min	Share your feedback on our TTS rate limits
Aura	Growth: Up to 720 requests / min	Share your feedback on our TTS rate limits

Text to Speech Streaming

Model	Service Limit	Feedback
Aura	Pay as You Go: Up to 40 concurrent requests	Share your feedback on our TTS rate limits
Aura	Growth: Up to 80 concurrent requests	Share your feedback on our TTS rate limits

Audio Intelligence

If you include Audio Intelligence features in requests to /listen, you will be subject to the service limits noted in the table below.

Model	Service Limit
Intent Recognition	Up to 10 concurrent requests
Entity Detection	Up to 5 concurrent requests
Sentiment Analysis	Up to 10 concurrent requests
Summarization	Up to 10 concurrent requests
Topic Detection	Up to 10 concurrent requests

Text Intelligence

Model	Service Limit
Intent Recognition	Up to 10 concurrent requests
Sentiment Analysis	Up to 10 concurrent requests
Summarization	Up to 10 concurrent requests
Topic Detection	Up to 10 concurrent requests

Enterprise

Starting limits to consider if you have an Enterprise Contract with Deepgram.

📘
New and existing Enterprise customers can request a Service Limit increase by discussing your needs with the Deepgram Sales Team.

Speech to Text

If multiple services are used in one API call (e.g Speech to Text + Sentiment Analysis), the lower of the rate limits is applied.

Model	Service Limit
Nova-2	`Pre-Recorded`Starting at 100 concurrent requests `Streaming` Starting at 100 concurrent requests
Nova	`Pre-Recorded`Starting at 100 concurrent requests `Streaming` Starting at 100 concurrent requests
Enhanced	`Pre-Recorded`Starting at 100 concurrent requests `Streaming` Starting at 100 concurrent requests
Base	`Pre-Recorded`Starting at 100 concurrent requests `Streaming` Starting at 100 concurrent requests
Whisper Cloud	`Pre-Recorded` Starting at 15 concurrent requests

Text to Speech REST

Model	Service Limit	Feedback
Aura	Starting at 2400 requests / min	Share your feedback on our TTS rate limits

Text to Speech Streaming

Model	Service Limit	Feedback
Aura	Starting at 150 concurrent requests	Share your feedback on our TTS rate limits

Audio Intelligence

If you include Audio Intelligence features in requests to /listen, you will be subject to the service limits noted in the table below.

Model	Service Limit
Intent Recognition	Starting at 10 concurrent requests
Entity Detection	Starting at 10 concurrent requests
Sentiment Analysis	Starting at 10 concurrent requests
Summarization	Starting at 10 concurrent requests
Topic Detection	Starting at 10 concurrent requests

Text Intelligence

Model	Service Limit
Intent Recognition	Starting at 10 concurrent requests
Sentiment Analysis	Starting at 10 concurrent requests
Summarization	Starting at 10 concurrent requests
Topic Detection	Starting at 10 concurrent requests

🚧
The error 429: Too Many Requests is returned when your project has more concurrent requests than the rate limits allow. To learn more about this error please see our Documentation on Errors.