Models

Select your model per message in the assistant composer. Gemini 3.5 Flash serves as the standard default for general tasks, while Gemini 3.1 Pro provides advanced reasoning capability.

Chat & Reasoning. Gemini 3.1 Pro, Gemini 3.5 Flash, Gemini 3.1 Flash Lite, Gemini 3.1 Deep Think, Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4 (standard, mini, and nano variants), Grok 4.3, Grok 4.1 Fast, Phi-4 mini and Phi-4 multimodal.
Open Architecture. Llama 4 Scout, Llama 4 Maverick, DeepSeek V3.2, Qwen 3 235B Instruct, Qwen 3 Coder 480B, Gemma 4 26B.
Media & Speech. Veo 3.1, Veo 3.1 Fast, and Veo 3.1 Lite for video generation; Nano Banana 2 and Nano Banana Pro for image generation; Chirp 3 for natural speech synthesis.

Daily token consumption is metered against a transparent quota visible in Account settings.