Release Notes

Recent changes to Big-AGI Pro, Free, and Open. For AI experts only.

For questions, comments, feedback, and support please use this link.
For bugs and features, open a github ticket - auto-fix within one hour.

Dec 4

• GPT 5.1 Codex Max support

Dec 2

• Deepseek V3.2 Speciale comes with almost Gemini 3 Pro performance but 20 times cheaper
• Mistral 3 family models, including Large 2512

Nov 30

• New text to speech & Voices: support for LocalAI, OpenAI, WebAudio (free) in addition to ElevenLabs
• Direct connection now available for all AI Services

Nov 24

• Anthropic Opus 4.5 with controls for effort (speed tradeoff), thinking budget, search, etc.
• Direct connection to cloud and local AI services from the browser for Anthropic, Google, LocalAI
• Thanksgiving promo: $10.99/mo locked forever, will increase after
• Released Open 2.0.1 on GitHub and Docker 

Nov 23

• UX changes: interleaved model thoughts, starred models display, persona starters, ai inspector fields
• Maximum privacy with option to connect directly from the browser to Anthropic, Gemini, and LocalAI

Nov 21

• Nano Banana Pro support including search, editing with up to 5 people/object references, image sizes and ratios

• Gemini models support encrypted signatures for native agentic continuation

Nov 20

• Grok 4.1 Fast support with automatic code execution and search
• Voice calls save the transcripts

Nov 19

• Gemini 3 Pro support including Browsing, Code execution, Thinking depth, Media resolution
• Image generation (/draw) with Azure and LocalAI
• Performance improvements

Nov 16

• OpenAI GPT-5.1 model family
• Social coding: “Improve Big-AGI“ support button for free Big-AGI feature development

Nov 13

• Advanced support for OpenRouter including reasoning, search, multimodal
• Improved OpenRouter integration with direct login

Nov 10

• Added Kimi K2 Thinking and more Moonshot AI models
• Reduced connection issues to overloaded AI servers by 85% thanks to 3 error correction methods

Nov 7

• Generate Persona images
• Chat chimes and spoken briefings - enable in chat options
• Fixes to login links with Outlook, added AI image attachment captioning, nanosecond-level optimizations

Nov 1

• Search toggle for beams
• Option to manually set per-model pricing

Oct 29

• Login with email, via magic link
• Released Open 2.0.0 on GitHub and Docker 
• Resilience: Auto-retry LLM calls when upstream servers are temporarily unavailable

Oct 23

• Search toggle to quickly turn on/off search for models that support it
• Change context window size for custom models

Oct 21

• Anthropic Search & Fetch support across models, making it the 5th provider with native search support
• Anthropic Sonnet 4+ models support 1M Token context windows
• Stability improvements, fixing Perplexity models and keyboard navigation

Oct 16

• Anthropic Haiku 4.5 models (standard and thinking variants)
• OpenAI GPT-5 Search API model for web-integrated responses
• Updated models across Anthropic, Mistral, Deepseek, Groq, xAI, Perplexity

Oct 14

• OpenAI Audio and Audio Mini models for audio output
• Gemini models support Google Search
• xAI Grok 4 Fast Reasoning and Grok Code Fast 1
• AI Request Inspector with quick toggle, for maximum transparency
• Mobile UI dialogs improvements

Oct 7

• OpenAI GPT-5 Pro and gpt-image-1-mini 

Oct 4

• Cloud Sync launched! - long awaited and top requested, available now on app.big-agi.com
• Dark launch - big thanks to the early testers

Sept 29

• Anthropic Claude Sonnet 4.5 support
• OpenAI GPT-5 Codex support
• Gemini 2.5 Flash Preview and Robotics-ER 1.5 support

Sept 28

• AI experts: view the exact AI API requests with the “AI Inspector” tool
• Address the next message to a specific @Persona (beginning of the message only)
• Beam: auto-select 4 good models at any time
• Persona: deep data comparison with live editing
• Improve personas image data support

Sept 17

• GPT-5 Image Generation: look for the option on the side pane. Also improved Search, Progress indication, Citations.
• Model controls and selection from the side panel

Sept 15

• Personas now support Image data, perfect for designer personas, especially with Gemini Nano Banana
• Drag to reorder personas in any list
• … Former release note entries are removed for space

Built for you

• Welcome to the new Big-AGI, this will feel like a brand new product. If you are here for the first time, welcome, and I hope you’ll love the obsession and mad optimization we put into this product, to give you the cleanest and most productive experience.

For AI experts only.