●TTS — Gemini 3.8 Flash TTS and Flash-Lite TTS are GA as of September 22. Voice replication works on Flash only; Flash-Lite returns a 400●2.5 — Access to the 2.5 models is now limited to accounts with prior active usage (September 18). Not a deprecation: new projects should start on 3.5 Flash-Lite or 3.8 Flash●9/30 — Two days until gemini-omni-flash-preview shuts down, and gemini-2.5-flash-image follows on October 2. In practice the replacement for the latter is gemini-3.1-flash-image●AUTH — Reports continue of Gemini CLI sign-in failing only for Workspace Enterprise accounts while personal accounts work. Isolating the two is the current focus●NEW — Moving to 3.8 Flash-Lite TTS meant re-picking the voice for our guidance audio●429 — A brand-new project shows Free tier yet returns 429 with limit: 0. Here is what to check in the first hour●TTS — Gemini 3.8 Flash TTS and Flash-Lite TTS are GA as of September 22. Voice replication works on Flash only; Flash-Lite returns a 400●2.5 — Access to the 2.5 models is now limited to accounts with prior active usage (September 18). Not a deprecation: new projects should start on 3.5 Flash-Lite or 3.8 Flash●9/30 — Two days until gemini-omni-flash-preview shuts down, and gemini-2.5-flash-image follows on October 2. In practice the replacement for the latter is gemini-3.1-flash-image●AUTH — Reports continue of Gemini CLI sign-in failing only for Workspace Enterprise accounts while personal accounts work. Isolating the two is the current focus●NEW — Moving to 3.8 Flash-Lite TTS meant re-picking the voice for our guidance audio●429 — A brand-new project shows Free tier yet returns 429 with limit: 0. Here is what to check in the first hour

TAG

countTokens

2 articles

← Back to all tags

gemini-api¹ multilingual¹ system instructions¹ cost design¹ python¹ Gemini API¹ Cost Management¹ Batch Processing¹ Production¹

⬡ 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.