Answer · Coding
What AI models does Lovable use?
Lovable runs on Chat Latest (openai/chat-latest) (OpenAI), Claude Opus 5 (Anthropic), Gemini (Google), Gemini 3.5 Transcribe (Google), Gemini 3.8 Flash (Google), Gemini Embedding 2 (google/gemini-embedding-2) (Google), Gemini Omni 1.1 Flash (Google), google/gemini-3.7-flash (Google), google/gemini-embedding-2 (Google), GPT Image 1 Mini (OpenAI), GPT Image 2 (OpenAI), GPT-6 Astra (OpenAI), openai/chat-latest (OpenAI) and Veo 3.1 (Google), and routes requests between them.
- Models used
- 14
- Primary model
- Chat Latest (openai/chat-latest)
- Public API
- Yes
- Last checked
- 2026-09-12
Model claims are labelled by how we know them: Chat Latest (openai/chat-latest) — disclosed, Claude Opus 5 — disclosed, Gemini — inferred, Gemini 3.5 Transcribe — disclosed, Gemini 3.8 Flash — disclosed, Gemini Embedding 2 (google/gemini-embedding-2) — disclosed, Gemini Omni 1.1 Flash — disclosed, google/gemini-3.7-flash — disclosed, google/gemini-embedding-2 — disclosed, GPT Image 1 Mini — disclosed, GPT Image 2 — disclosed, GPT-6 Astra — disclosed, openai/chat-latest — disclosed and Veo 3.1 — disclosed. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.
Context window: Varies by model.
Other stack signals: React, Vite, TanStack Start, GitHub, Stripe, Paddle, PostHog, Shopify, Notion, Pipedrive, Amazon Redshift and Microsoft Fabric.
Cite this answer
Tomorrow. “What AI models does Lovable use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-09-12. https://tomorrow.aliensquad.ai/q/what-models-does-lovable-use
Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →