The outcome

Select a model based on measured quality, cost, latency, safety, and operational fit.

Step by step

A workflow you can repeat.

  1. 01

    Define the workload, modalities, context, output schema, license constraints, safety cases, budget, and scoring method.

  2. 02

    Shortlist current serverless models and verify capability, pricing, deprecation status, and provider documentation.

  3. 03

    Run identical examples with fixed settings and record outputs, latency, token use, cost, refusals, and formatting failures.

  4. 04

    Use a held-out evaluation set or the evaluation service to compare finalists without tuning prompts to individual examples.

  5. 05

    Choose a primary and compatible fallback, pin model identifiers, and establish regression thresholds for future changes.

Working standard

What good use looks like.

  • Evaluate your real task.
  • Keep a held-out test set.
  • Record the exact model and parameters.

Official references

Check the current product documentation.