●SUNSET — Five days until the imagen-4.0 family shuts down: imagen-4.0-generate-001 and two sibling models stop on August 17●SAMPLING — Since July 21 the temperature, top_p, and top_k parameters are deprecated; no shutdown date yet, but worth auditing your calls●API — The Interactions API is now generally available and is the recommended path to the latest models and features●ROBOTICS — gemini-robotics-er-1.6-preview shuts down on August 31; its successor, ER 2, has been in public preview since July 30●ENTERPRISE — The Gemini Enterprise mobile app reached GA for organizations authenticating through third-party identity providers●RENAME — NotebookLM Enterprise is now Gemini Notebook Enterprise, so the term to search the docs for has changed too●SUNSET — Five days until the imagen-4.0 family shuts down: imagen-4.0-generate-001 and two sibling models stop on August 17●SAMPLING — Since July 21 the temperature, top_p, and top_k parameters are deprecated; no shutdown date yet, but worth auditing your calls●API — The Interactions API is now generally available and is the recommended path to the latest models and features●ROBOTICS — gemini-robotics-er-1.6-preview shuts down on August 31; its successor, ER 2, has been in public preview since July 30●ENTERPRISE — The Gemini Enterprise mobile app reached GA for organizations authenticating through third-party identity providers●RENAME — NotebookLM Enterprise is now Gemini Notebook Enterprise, so the term to search the docs for has changed too

TAG

Quality Gate

1 articles

← Back to all tags

Gemini API¹ Deep Think¹ Flash¹ Cost Optimization¹

◈ Gemini API/2026-06-14Intermediate

Generate With Flash, Escalate to Deep Think Only When Unsure: A Two-Stage Pipeline

With Deep Think opening up on the API, the move is not to route every request through the heavy model but to have Deep Think verify only when Flash's output looks shaky. Here is the cost reasoning and working code.