Explore the planning tools before making a provider request. Choose the tool that resolves your current uncertainty and keep its assumptions with the result.

Cost and workload

AI API cost calculator — compare model workloads and inspect the assumptions behind an estimate.

Text and model selection

Token counter — inspect text length with a supported tokenizer or labelled estimate.

Model finder — narrow the published catalog by documented attributes.

Comparison and changes

Compare models or providers — keep relevant attributes side by side.

Price history — inspect recorded model-price changes.

Use the result well

Keep the selected model, unit and verification date with an estimate. A missing field is an unresolved fact, and a capability-based shortlist is not an independent quality benchmark. Test candidate outputs against representative tasks before making the final selection.

Last verified · Source ↗

Frequently asked questions

What does this site help me choose?
An API provider and model for an application task, with documented attributes, cost assumptions and implementation guidance kept together.
Do the tools make paid model requests?
The planning tools use the site’s reference data. Provider inference belongs to the separate scripts you choose to run with your own authorized credential.
Is the cheapest listed model always the right choice?
No. Evaluate accepted task completion and the full workload before deciding.
Why can a model field be missing?
The required evidence may not be available or verified. Missing information is not a free price or an unlimited capability.
Are quality rankings independent benchmarks?
A documented capability or fit-based shortlist is not an independent benchmark. Use your own representative evaluation for quality claims.

Sources

Last verified · Source ↗