Answer · Coding
What AI models does Lovable use?
Lovable runs on bytedance/seedance-2.5 (ByteDance), bytedance/seedream-5-pro (ByteDance), Chat Latest (openai/chat-latest) (OpenAI), Claude (Anthropic), Claude Fable 5.1 (Anthropic), Claude Haiku 4.5 (Anthropic), Claude Opus 5 (Anthropic), Claude Opus 5.5 (Anthropic), Claude Sonnet 5 (Anthropic), Gemini (Google), Gemini 3.1 Flash Lite (Google), Gemini 3.5 Transcribe (Google), Gemini 4 Argon (Google), Gemini Embedding 2 (google/gemini-embedding-2) (Google), Gemini Omni 1.1 Flash (Google), google/gemini-3.7-flash (Google), google/gemini-3.8-flash (Google), google/gemini-embedding-2 (Google), GPT Image 1 Mini (OpenAI), GPT Image 2 (OpenAI), GPT Image 2.5 Flare (OpenAI), GPT Image 2.5 Sunburst (OpenAI), GPT Image 2.6 Flare (OpenAI), GPT Image 2.6 Sunburst (OpenAI), GPT Live (OpenAI), GPT Transcribe (openai/gpt-transcribe) (OpenAI), GPT-6 Astra (OpenAI), GPT-6 Luna (OpenAI), GPT-6 Sol (OpenAI), GPT-6.1 Sol (openai), GPT-6.1 Sol (openai/gpt-6.1-sol) (OpenAI), Jev Latest (TypeSafe), LlamaParse Platform (LlamaIndex), Lyria 3 Clip Preview (Google), Lyria 3 Pro Preview (Google), openai/chat-latest (OpenAI), openai/gpt-transcribe (OpenAI), Seedance 2.5 (ByteDance), Seedream 5 Pro (ByteDance), Topaz Starlight Fast 2 (topazlabs) and Veo 3.1 (Google), and routes requests between them.
- Models used
- 41
- Primary model
- bytedance/seedance-2.5
- Public API
- Yes
- Last checked
- 2026-11-08
Model claims are labelled by how we know them: bytedance/seedance-2.5 — disclosed, bytedance/seedream-5-pro — disclosed, Chat Latest (openai/chat-latest) — disclosed, Claude — unknown, Claude Fable 5.1 — disclosed, Claude Haiku 4.5 — disclosed, Claude Opus 5 — disclosed, Claude Opus 5.5 — disclosed, Claude Sonnet 5 — disclosed, Gemini — inferred, Gemini 3.1 Flash Lite — disclosed, Gemini 3.5 Transcribe — disclosed, Gemini 4 Argon — disclosed, Gemini Embedding 2 (google/gemini-embedding-2) — disclosed, Gemini Omni 1.1 Flash — disclosed, google/gemini-3.7-flash — disclosed, google/gemini-3.8-flash — disclosed, google/gemini-embedding-2 — disclosed, GPT Image 1 Mini — disclosed, GPT Image 2 — disclosed, GPT Image 2.5 Flare — disclosed, GPT Image 2.5 Sunburst — disclosed, GPT Image 2.6 Flare — disclosed, GPT Image 2.6 Sunburst — disclosed, GPT Live — disclosed, GPT Transcribe (openai/gpt-transcribe) — disclosed, GPT-6 Astra — disclosed, GPT-6 Luna — disclosed, GPT-6 Sol — disclosed, GPT-6.1 Sol — disclosed, GPT-6.1 Sol (openai/gpt-6.1-sol) — disclosed, Jev Latest — disclosed, LlamaParse Platform — inferred, Lyria 3 Clip Preview — disclosed, Lyria 3 Pro Preview — disclosed, openai/chat-latest — disclosed, openai/gpt-transcribe — disclosed, Seedance 2.5 — disclosed, Seedream 5 Pro — disclosed, Topaz Starlight Fast 2 — 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: Drizzle and TanStack Start.
Cite this answer
Tomorrow. “What AI models does Lovable use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-11-08. 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 →