Skip to content
Trending storyDeveloping

Google Cloud publishes developer guide to Long Decode for Gemini 4 Argon

1 article1 sourcesince Oct 13Last article 1h ago ·

Overview

AISummary of 1 article

Google Cloud Tech publishes a developer guide explaining how Long Decode lets Gemini 4 Argon return completions up to 1M tokens by splitting one generation across several model inferences.

Developers can enable it through the latest Gen AI SDKs or by manually handling a continuation_token, with max_output_tokens set above 65,536 for streaming or 32,768 for unary requests. Long Decode is not enabled by default.

The post says billing for completions above 32K tokens starts November 13, 2026, with the GenerateContent API charging for output beyond 32K tokens and then every 5K tokens after that.

Written by AI from the articles below · updated Oct 13, 3:39 PM ET

Check the sources:

Latest developmentOct 13, 3:24 PM ET
Developer guide to Gemini 4 Argon Long Decode

Article timeline

The articles in this story. Times are ET.

Oct 13
  1. Google Cloud TechOfficialPick
    Developer guide to Gemini 4 Argon Long Decode

    AIGoogle Cloud Tech explains how Long Decode lets Gemini 4 Argon return completions up to 1M tokens by splitting one generation across several model inferences. Developers can enable it through the latest Gen AI SDKs or by manually handling a continuation_token, with max_output_tokens set above 65,536 for streaming or 32,768 for unary requests. The post also notes that billing for completions above 32K tokens starts November 13, 2026.

Heat trend

Not enough continuous observations to show a trend yet.