OpenAI's fastest, cheapest frontier model — great default.
No signup required — 10,000 session credits for guests. 50,000 free credits on account creation.
GPT-4o mini is OpenAI's small-but-capable model — roughly 25× cheaper per token than full GPT-4o, with quality that's plenty for everyday tasks. The default pick when you want OpenAI quality at fraction cost.
Dramatically cheaper per message than GPT-4o
Still handles vision (at a reduced fidelity)
Sub-second first token in most cases
128k context window
Around 200–450 credits per typical message. A 50k signup bonus buys around 125 messages.
GPT-4o mini is OpenAI's smaller, faster, much cheaper sibling to full GPT-4o — released in July 2024 to replace GPT-3.5-turbo. It keeps multimodal support.
Use mini for summarisation, day-to-day Q&A, drafting emails, quick code explanations. Reach for full GPT-4o when the task needs deep reasoning or careful code architecture.
You get 50k credits on signup. A GPT-4o mini message costs ~200–450 credits, so that's roughly 100+ free messages.
For boilerplate and small edits, yes. For architecture-level refactors, Claude 3.5 Sonnet or full GPT-4o are better picks.
Yes, it accepts image input — at reduced fidelity compared to full GPT-4o, but plenty for screenshots and diagrams.
128,000 tokens, same as full GPT-4o.
Both are small-and-fast. Claude Haiku has a larger context window (200k vs 128k); GPT-4o mini has better multimodal support. Try both and pick.
Yes. Any API key from /account/api/ can call it. Model slug: openai/gpt-4o-mini.
It's a much smaller model — fewer parameters means cheaper inference. The trade-off is slightly weaker reasoning, but the cost difference is 20-30×.
Yes — same Oct 2023 cutoff in practice, with some refreshes via OpenAI's training pipeline.
Yes — it inherits OpenAI's moderation. Pair it with a clear system prompt and a PII-stripping pass if you're logging transcripts.
As long as OpenAI serves it. If they deprecate it (they announced one-year notice policies), we'll surface a replacement in the picker before it goes dark.
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 fastest, cheapest model — near-instant replies.
Chat with Claude 3 Haiku →Google's fast multimodal model with a 1M-token context window.
Chat with Gemini 2.0 Flash →One subscription covers every frontier model — switch between them per message. No extra API keys, no extra bills.