Google's fast multimodal model with a 1M-token context window.
No signup required — 10,000 session credits for guests. 50,000 free credits on account creation.
Gemini 2.0 Flash is Google DeepMind's fast multimodal model, notable for its 1M-token context window (you can paste a whole novel and still have room). Native vision, audio input, and tool use.
1,000,000-token context window (largest anywhere)
Native multimodal — text, images, audio-in
Very fast streaming
Strong at grounded tasks when given enough context
Often free-tier at 0 credits per call (with upstream rate-limits); paid tier is a few hundred credits.
Gemini 2.0 Flash is Google DeepMind's fast multimodal model — released Dec 2024. Notable for its 1M-token context window and native audio/image input.
Anything that benefits from huge context — reading PDFs, entire codebases, long transcripts. Also solid at visual reasoning.
No. Faceb.ai gives you Gemini 2.0 Flash alongside every other model on one plan — no Google subscription needed.
Google offers a rate-limited free tier that sometimes returns $0 cost; when it does, it's essentially free to use here. Heavy use gets rate-limited upstream.
Flash wins on context (1M vs 128k) and latency. GPT-4o edges ahead on deep reasoning and creative writing. Gemini is often the cheaper pick.
Yes — native audio input is one of its headline features. Drop an audio file and it transcribes + reasons in one pass.
Yes — our picker has it too. Pro is larger and smarter but slower and pricier than Flash.
Yes. Model slug: google/gemini-2.0-flash-exp:free (free tier) or the paid variant. OpenAI-compatible endpoint at https://api.faceb.ai/v1.
It's improving fast, but still a half-step behind Claude 3.5 Sonnet and GPT-4o for code tasks. Great at explaining code you paste in with its huge context window, though.
Varies by Gemini version; 2.0 Flash is roughly June 2024. Google refreshes periodically.
We route through upstream providers with a no-training request. For Google's free tier specifically, their default terms may include training rights — switch to the paid tier or a different provider if that's a concern.
Yes — our catalog auto-fetches from the upstream aggregator, so new Google models appear in the picker on release day.
Your Faceb.ai credits work for every model — switch per message, no extra subscriptions.
OpenAI's flagship multimodal model — text, vision, and code.
Chat with GPT-4o →Anthropic's best balance of quality and cost — a coder favourite.
Chat with Claude 3.5 Sonnet →Meta's best open-weight model — runs on community hosts.
Chat with Llama 3.3 70B →One subscription covers every frontier model — switch between them per message. No extra API keys, no extra bills.