◉GEMINI LABJP
●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

countTokens

2 articles
← Back to all tags
Related:
gemini-api1multilingual1system instructions1cost design1python1Gemini API1Cost Management1Batch Processing1Production1
⬡ Gemini Advanced/2026-07-16Advanced

What language should your system instruction be in? Measuring three approaches when most prompts arrive in the user's language

Keep the system instruction in English, or translate it into the user's language? I measured input tokens per language with countTokens, then lined up output-language match and schema compliance to find where nine tokens is enough.

◈ Gemini API/2026-06-18Advanced

Stop a Batch Before It Overspends — A Budget Gate Built on countTokens That Survives a Default-Model Swap

Nightly batches overspend because you only learn the cost after billing. Starting from countTokens, this guide builds a budget gate that folds in thinking tokens and keeps your estimate intact even when the default model changes underneath you.