OpenAI

OpenAI Evals API

The Evals API allows you to programmatically configure and run evaluations to test model outputs against your expectations. Evaluations ensure model responses meet style and content criteria you specify, and are essential for building reliable LLM applications, especially when upgrading or trying new models.

GitHub

Documentation

📖
Documentation
https://platform.openai.com/docs/api-reference/evals
📖
Documentation
https://platform.openai.com/docs/guides/evals

API entry from apis.yml

apis.yml Raw ↑ 
aid: openai:openai-evals-api
name: OpenAI Evals API
tags:
- Evals
- Evaluation
- Testing
score: 100
baseURL: https://api.openai.com
humanURL: https://platform.openai.com/docs/api-reference/evals
properties:
- url: https://platform.openai.com/docs/api-reference/evals
  type: Documentation
- url: https://platform.openai.com/docs/guides/evals
  type: Documentation
description: The Evals API allows you to programmatically configure and run evaluations to test model
  outputs against your expectations. Evaluations ensure model responses meet style and content criteria
  you specify, and are essential for building reliable LLM applications, especially when upgrading or
  trying new models.