llm-gemini 0.31

📰 Simon Willison's Blog

Learn about the latest release of llm-gemini 0.31 and its features, and why it matters for AI model development

intermediate Published 7 May 2026
Action Steps
  1. Read the release notes for llm-gemini 0.31 to understand its new features
  2. Explore the gemini-3.1-flash-lite model and its capabilities
  3. Test the model using sample inputs to evaluate its performance
  4. Compare the results with previous versions of the model
  5. Apply the new features of llm-gemini 0.31 to existing AI projects
Who Needs to Know This

AI engineers and researchers can benefit from this update to improve their AI model development, and product managers can consider integrating this model into their products

Key Insight

💡 The gemini-3.1-flash-lite model is now out of preview and available for use in production environments

Share This
🚀 llm-gemini 0.31 is out! 🤖

Full Article

Release: llm-gemini 0.31 gemini-3.1-flash-lite is no longer a preview . Here's my write-up of the Gemini 3.1 Flash-Lite Preview model back in March.
Read full article → ← Back to Reads

Related Videos

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
GLM_5-2
GLM_5-2
Hyperstack
LongCat 2.0: N-Grams Beat More Experts
LongCat 2.0: N-Grams Beat More Experts
Prompt Engineering
Sonnet 5, more expensive than opus?
Sonnet 5, more expensive than opus?
Prompt Engineering
Gemini Omni Flash: Anything to Anything model from Google
Gemini Omni Flash: Anything to Anything model from Google
Prompt Engineering
Claude Fable 5 Is BACK (And It's Different)
Claude Fable 5 Is BACK (And It's Different)
Creator Magic