GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features
- Released
- Sep 8, 2026
- Plan
- All plans
- Source
- docs.lovable.dev
GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features is Lovable's Editor feature: Your app's AI features can now use three new models: Ask Lovable to use any of these models in your app, or describe what you want and let….
Your app's AI features can now use three new models: Ask Lovable to use any of these models in your app, or describe what you want and let Lovable pick.
How it works
How GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features works, drawn only from its official release notes.
What it does
Your app's AI features can now use three new models: Ask Lovable to use any of these models in your app, or describe what you want and let Lovable pick.
What the release notes list
GPT-6 Astra , OpenAI's most capable model for complex reasoning, coding, research, and document creation. It comes at a premium price; Gemini 3.8 Flash , the new default chat model. It accepts text, image, audio, and video input; Gemini 3.5 Transcribe , the new default speech-to-text model. It detects the spoken language automatically across more than 85 languages.
Who gets it
Plan availability per the source: All plans.
Example workflows
Starting points built from this record, not transcripts of a run. Each prompt is written the way it should be sent, as one paragraph, and each is worth editing before you send it.
Stand it up from scratch
You have read the record and want GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features working in a real project rather than a sandbox.
Set up GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features in this project — your app's AI features can now use three new models: Ask Lovable to use any of these models in your app, or describe what you want and. Walk it end to end, tell me exactly what you changed, and flag anything I have to switch on myself before it works.
Expected outcomeA working setup, a plain list of what changed, and a short list of anything left for you to switch on. Check that list before assuming it is done.
Review it before you publish
GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features is wired in and you are about to put it in front of people. This is the pass that catches the half-configured version.
Review how this project uses GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features before I publish. Check GPT-6 Astra , OpenAI's most capable model for complex reasoning, coding, research, and document creation. It comes at a premium price and gemini 3.8 Flash , the new default chat model. It accepts text, image, audio, and video input, list anything that is missing, misconfigured, or only half wired, fix what is safe to fix, and tell me what you left alone and why.
Expected outcomeA findings list split into what was fixed and what was left, with a reason for each. Anything left alone is yours to decide on.
Decide whether it fits your project
Worth five minutes before you wire anything in. GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features sits in Editor, and not every project needs it.
I am building the project in this workspace. Given that GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features your app's AI features can now use three new models: Ask Lovable to use any of these models in your app, or describe what you want and, tell me honestly whether it fits what I am building, including the cases where I should not use it. If it does fit, give me the single smallest first step.
Expected outcomeA direct yes or no with the reasoning, the cases against it, and one first step. Treat a hedged answer as a no.
Capabilities
- GPT-6 Astra , OpenAI's most capable model for complex reasoning, coding, research, and document creation. It comes at a premium price.
- Gemini 3.8 Flash , the new default chat model. It accepts text, image, audio, and video input.
- Gemini 3.5 Transcribe , the new default speech-to-text model. It detects the spoken language automatically across more than 85 languages.
The link to lovable.dev uses a referral code. The atlas is otherwise unsponsored.
Frequently asked
What is GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features?
GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features is Lovable's Editor feature: Your app's AI features can now use three new models: Ask Lovable to use any of these models in your app, or describe what you want and let…. Your app's AI features can now use three new models: Ask Lovable to use any of these models in your app, or describe what you want and let Lovable pick.
Is GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features GA or in beta?
GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features is generally available (GA) on Lovable.
What Lovable plan includes GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features?
GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features is available on all Lovable plans.
When did GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features launch?
GPT-6 Astra, Gemini 3.8 Flash, and Gemini 3.5 Transcribe for your app's AI features launched on Sep 8, 2026.
What Lovable Shipped
Get every new Lovable feature by email.
A curated Monday roundup of every Lovable feature added or promoted to GA in the past week — pulled straight from the atlas.
No spam. Unsubscribe anytime. Independent, not affiliated with Lovable AB.