Deepgram · Rate Limits
Deepgram Rate Limits
Deepgram concurrent connection limits.
Deepgram Rate Limits is the machine-readable rate-limit profile for Deepgram on the APIs.io network, in the API Commons Rate Limits shape.
It captures 4 rate-limit definitions, measuring concurrent.
Limit state is signalled in the retryAfter response header, and an exhausted limit returns HTTP 429.
This profile was written by API Evangelist and has not been verified against a page the provider published; treat every limit as unconfirmed until a dated transcription replaces it.
The profile also includes response codes documented for throttled and concurrencyExceeded.
Tagged areas include Rate Limiting and Speech.
4 Limits
Exhausted: HTTP 429
retryAfter
Method:
generated, dated 2026-05-04.
Written by API Evangelist on 2026-05-04 and not verified against a page the provider published. Treat every limit as unconfirmed until a dated transcription replaces it.
View Source
Rate LimitingSpeech
Limits
Streaming concurrent (Pay-as-you-go) project
50
Pre-recorded concurrent (Pay-as-you-go) project
100
Streaming concurrent (Growth) project
100
Streaming concurrent (Enterprise) project
custom
Sources
- https://deepgram.com/pricing
- https://developers.deepgram.com/docs/working-with-concurrency-rate-limits
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.