June 🎉 GPT 15% Off 🎉 All series, all month 🔥Learn more

Frequently asked questions

How does the Model Finder pick models?+

It scores every non-deprecated model on Ofox across four axes — quality, cost, speed, and fit for your use case — then weights them by the priority you choose. Quality reflects model tier and capabilities, cost uses real per-token pricing, and fit measures whether a model is tuned for your task (coding, vision, long context, and so on).

Is it free? Do I need an account?+

Yes, it's completely free and runs in your browser — no login or API key needed to get recommendations. You only need an Ofox account when you're ready to actually call a model.

Are these real, up-to-date models?+

Every recommendation comes from the live Ofox catalog of 100+ models, refreshed continuously. The pricing and context windows shown are pulled directly from the catalog.

Why doesn't the cheapest model always rank first?+

Unless you pick 'Lowest cost', the finder balances price against quality and capability. A model that costs a little more but is much more capable will often score higher — just like a person would choose.

Can I use the recommended models with my existing code?+

Yes. Every model is available through one OpenAI-, Anthropic-, or Gemini-compatible endpoint. Change the base URL and API key and your existing SDK works unchanged.

Found your model? Start building.

One API key, 100+ models, no rate limits. Free tier included — no card required.

Get your free API key