Google Enterprise Agent API support
UpdateUnverifiedAdded Sep 24, 2026
Managed Google LLMs now run on either of Google's APIs: the AI Studio API or the Gemini Enterprise Agent (GEA) API, formerly the Vertex API. GEA adds regional Google endpoints for models where available. Select the API with think.provider.version from any Deepgram Voice Agent endpoint: ai-studio-v1beta for AI Studio, gemini-enterprise-agent-v1 for GEA.
Topics: AI agents, LLMs, Developer tools, Regions
More Deepgram releases
Every Deepgram release| Date | Release | Type |
|---|---|---|
| Jul 31 | UpdateListen: switch model and language mid-sessionunverified Update | Update |
| Jul 31 | STT latency in LatencyReportunverified Update | Update |
| Jul 31 | Maximum session length of 2 hoursunverified Update | Update |
| Jul 31 | Fixedunverified Update | Update |
| Jul 28 | Container Images (release 260728)unverified Update | Update |
| Jul 28 | FIPS 140-3 Images (General Availability)unverified GA | GA |
| Jul 28 | This Release Contains The Following Changesunverified Update | Update |
| Aug 4 | Improved Models Released for Multiple Languagesunverified Update | Update |
Also shipped on Jul 31, 2026
Deepgram in July 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.