Skip to content

Reasoning mode for OpenAI thinking models

UpdateUnverifiedAdded Sep 24, 2026

You can now control the reasoning effort of supported OpenAI reasoning models using the new reasoning_mode parameter in the think provider configuration. This parameter maps to OpenAI's reasoning_effort and accepts low , medium , or high .

Topics: AI agents, LLMs

Deepgram's release notes

More Deepgram releases

Every Deepgram release
DateRelease
Mar 10Nova-3 Model Updateunverified
Update
Mar 5Container Images (release 260305)unverified
Update
Mar 5This Release Contains The Following Changesunverified
Update
Mar 16๐Ÿค– New LLM Models Support & Bug Fixesunverified
Preview
Mar 16Fixesunverified
Update
Mar 17Nova-3 Model Updateunverified
Update
Mar 19Container Images (release 260319)unverified
Update
Mar 19This Release Contains The Following Changesunverified
Update

Also shipped on Mar 9, 2026

Deepgram in March 2026

Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.

New releases by email

Tuesday mornings: the week's data, AI and developer-tools releases, only in weeks when something shipped.

Double opt-in. Unsubscribe any time.