AI BriefingNano Banana 2, AI Gateway Launch
Key point
Gemini 3.1 Flash Image Preview (Nano Banana 2) has launched on AI Gateway, offering enhanced visual quality and reasoning capabilities.
Details
Gemini 3.1 Flash Image Preview (codenamed Nano Banana 2) has launched on AI Gateway. This model is characterized by improved visual quality while maintaining the fast generation speed and low cost of Flash-tier models.
Key features include:
- Google Image Search integration: searches real-time visual data to accurately render unfamiliar landmarks or objects.
- Thinking Levels configuration: 'Minimal' and 'High' modes allow control over the model's reasoning process for complex prompts.
- New resolutions and aspect ratios: new specifications such as 512p, 1:4, and 1:8 have been added to support the creation of diverse creative assets.
Users can set the model name to google/gemini-3.1-flash-image-preview in the AI SDK to leverage multimodal capabilities that generate text and images simultaneously. AI Gateway supports model invocation, usage and cost tracking, retries, and failover through a unified API, ensuring high uptime.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Perplexity: AI Agents Bypass SPACE Network Policies; Direct Tests Reveal Weaknesses in 7 of 9 Third-Party SandboxesMeta Releases FLAT, a Variable-Length Continuous Token Model Integrating Image and Text