

The GPT-4.1 family is now live on Retell AI! Hereās how the models compare:
Intelligence:
GPT 4.1 > GPT 4o mini > GPT 4o > GPT 4.1 mini > GPT 4.1 nano
Latency (lower is faster):
GPT 4.1 nano < GPT 4.1 mini < GPT 4o mini < GPT 4o < GPT 4.1
Price (per minute):
GPT-4.1 nano ($0.004) < GPT-4o mini ($0.006) < GPT-4.1 mini ($0.016) < GPT-4.1 ($0.045) < GPT-4o ($0.050)
ā

You can now create and manage agent versions directly in the Agent Builder:
⢠Make changes and test your agent safelyāwithout affecting your live production calls.
⢠Revert to any previous version with a single click.
Just hit the āDeploymentā button to save a version, and use the history button to view and restore previous versions.
ā

You can now enter dynamic variables when sending a test call directly from the platformāmaking it easier to simulate real scenarios during testing.
Note: The test call will automatically pull in the dynamic variables youāve set in the agent configuration.
ā

Multilingual has updated!
Now support seamlessly switching between English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, Dutch.
(using nova 3)
ā

Weāve also added support for 10 more languages:
Romanian, Danish, Finnish, Greek, Indonesian, Norwegian, Slovak, Swedish, Bulgarian, Hungarian.
ā

If you want to prevent unauthorized access in case the URL is leaked, you can opt in for secure URLs. Secure URLs automatically expire 24 hours after they are generated, providing an additional layer of security.