EXVIV evidence profile

Google Gemini API

https://ai.google.dev/gemini-api

Review verified moves first. Open the official source or before-and-after evidence when you need the full record.

Public proof receipts

The useful part, first.

These are delayed P0 and P1 receipts from the curated public set. Same-day coverage and the rest of the watchlist stay in a private workspace.

P1packagingSep 15, 2026

The product’s packaging or offer changed.

BEFORE

Lyria 3.5 in public preview: Released the next generation of Google's music generation model: lyria-3.5: Full-length song generation with improved musical coherence, natural vocals, and fine-grained duration and structural control. The model supports text and image inputs and generates high-fidelity 44.1 kHz stereo audio. See the Music generation guide for details and code samples.

AFTER

September 15, 2026

View evidence

Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking are generally available as new audio-to-audio models for real-time voice applications using the Live API. Lyria 3.5 is generally available as the next generation of Google's music generation model, supporting full-length song generation with text and image inputs.

WHY IT MAY MATTER

A new release or deprecation can change feature parity, migration risk, and the next competitive response.

Open public receipt → Current source ↗

P1featureAug 27, 2026

Google adds Java SDK support to the Gemini API

BEFORE

auto_awesome Gemini 3.1 Pro New

AFTER

Java

View evidence

The Gemini API developer documentation now includes a Java language tab alongside Python, JavaScript, and REST, with a working code sample using com.google.genai.Client. This expands the official SDK surface for the Gemini API to four languages. (Verified against live docs at ai.google.dev/gemini-api/docs.)

WHY IT MAY MATTER

A documented capability change may alter product comparisons, roadmap priorities, or customer objections.

Open public receipt → Current source ↗

P1featureAug 25, 2026

Gemini API Interactions API becomes default; generateContent marked legacy.

BEFORE

The Interactions API is the best way to build with Gemini API and Gemini models and agents. Learn more in the Interactions API Overview.

AFTER

Interactions API

View evidence

Google's Gemini API documentation now states the Interactions API 'has become our default interface as of June 2026' and that developers starting new projects should use it, while explicitly marking the prior generateContent endpoint as 'legacy.' New migration guide (generateContent → Interactions) and streaming docs for real-time tokens, incremental thoughts, and tool-call events were added alongside.

WHY IT MAY MATTER

A documented capability change may alter product comparisons, roadmap priorities, or customer objections.

Open public receipt → Current source ↗

Monitored sources