openai · OpenAI Platform Docs
Model selection
A framework for selecting LLMs by prioritizing accuracy targets before optimizing for cost and latency, including methods for setting accuracy goals, creating evaluation datasets, and using prompt baking for future di...
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Model selection
A framework for selecting LLMs by prioritizing accuracy targets before optimizing for cost and latency, including methods for setting accuracy goals, creating evaluation datasets, and using prompt baking for future di...
When To Use
Use when deciding between high-capability models like GPT-4o and smaller models like GPT-4o-mini to balance performance requirements against budget and speed constraints.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/model-selection-workflow-guide.md | A guide outlining principles for choosing between OpenAI models based on accuracy, latency, and cost. | Questions about a guide outlining principles for choosing between OpenAI models based on accuracy, latency, and cost. |
What This Skill Covers
- Choosing the right model, whether GPT-4o or a smaller option like GPT-4o-mini, requires balancing accuracy, latency, and cost. This guide explains key princi...
- Main sections:
Core principles,1. Focus on accuracy first,Setting a realistic accuracy target,2. Optimize cost and latency,Exceptions to the rule.
Workflow
- Open the most relevant file under
docs/for the exact documented workflow and wording. - Open
schemas/files for exact structured contracts. - Open
examples/files for concrete requests, commands, snippets, and manifests. - Do not add behavior or configuration that is not present in the attached source files.
Canonical source: https://developers.openai.com/api/docs/guides/model-selection.md
