Choose an open model: compare fit, quality and cost
Start with the task and the input it needs.
Shortlist models that can handle both, compare their full token costs and test them on your own examples before choosing.
The short version
The lowest token price is useful only if the model completes your task.
Our model library lists capabilities, input types, context limits and prices to help you build a shortlist. We’ll use a hypothetical document assistant: users provide a contract and ask questions about it.
- Shortlist01Match model to taskWrite down what the feature needs first, and keep different jobs separate: retrieval and answering are different roles.
- 02Fit the longest requestsAn average request can fit while an important customer’s request fails.
- Compare03Price your token mixThe same token mix costs $13.00 to $255.00 a day by model, and even that assumes every repeated prefix is cached.
- 04Test on your own promptsPublic benchmarks measure other tasks; a fixed test set of your own real requests makes the final choice.
- Release05Record the exact modelA specific model ID makes the choice explicit, not permanent: check retirement notices and rerun tests before releases.
