v2.0.1
juliangarnier/animev2.0.1Nov 24, 2025by enricoros
AI Summary
This update expands model support with new AI families like GPT-5.1, Grok 4.1 Fast, and Kimi K2 Thinking. It also enhances image generation capabilities by adding Azure and LocalAI support, improves error resilience, and adds automatic call transcript saving.
Key Highlights
- New AI models (Gemini 3 Pro, Nano Banana Pro, Grok 4.1 Fast, GPT-5.1, Kimi K2 Thinking)
- Enhanced Image Generation (Azure and LocalAI support)
- OpenRouter auto-detection of capabilities
- Automatic call transcript saving
- Improved error resilience (85% reduction)
New Features
- Gemini 3 Pro with code execution
- Nano Banana Pro for controllable image generation
- Image generation support for Azure and LocalAI
- OpenRouter auto-detection of model capabilities and reasoning
- Automatic saving of call transcripts
- Persona image generation
- Search functionality in Beam
Full Release Notes
# Big-AGI 2.0.1 - Heavy Critters ## What's New ### **Latest Models** - **Gemini 3 Pro** with code execution support - **Nano Banana Pro** for controllable image generation - **Grok 4.1 Fast**, the **GPT-5.1** family, **Kimi K2 Thinking** - Updated model definitions across all 17+ providers ### **Enhanced Features** - **Image Generation** now supports Azure and LocalAI alongside OpenAI - **OpenRouter** auto-detects model capabilities and reasoning - Call transcripts saved automatically - Generate **persona images** - Search functionality in Beam ### **Improvements** - Enhanced error resilience (85% reduction in connection issues) - 280 commits of fixes and optimizations - [AI-Automatic feature development](https://github.com/enricoros/big-agi/issues/new?template=ai-triage.yml) for community contributions <img width="1792" height="1024" alt="release-cover-v2 0 0" src="https://github.com/user-attachments/assets/35ea95cf-896e-403f-bfe4-3aca59fd11a1" /> **Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.0...v2.0.1 ## Get Started Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.