Add “Selecting a Model Based on Stripe Conversion” notebook

[joshbickett]

Summary

Adds a new notebook “Selecting a Model Based on Stripe Conversion: A Practical Eval for Startups.”
The post walks through HyperWrite’s real-world A/B-test workflow for choosing an LLM using Stripe payment conversion as the success metric.

Motivation

Benchmark scores may fail to predict whether users will pay.
This guide shows startups how to evaluate and pick a cheaper or higher-performing model based on revenue-linked conversion data, not offline metrics. It fills a gap in the cookbook by providing:

• A step-by-step, production-tested A/B methodology
• Ready-to-run stats code (one-tailed Z-test)
• Concrete cost-savings case study (GPT-4.1 vs. Claude 3.5 Sonnet)

The pattern is directly applicable to any OpenAI-powered app that charges through Stripe.

For new content

When contributing new content, read through our contribution guidelines, and mark the following action items as completed:

• I have added a new entry in registry.yaml (and, optionally, in authors.yaml) so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the contribution guidelines:
  • Relevance: This content is related to building with OpenAI technologies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.

[joshbickett]

@shyamal-anadkat @Lupie here is the PR for your review!

[Copilot]

Pull Request Overview

Adds a new notebook demonstrating how to choose an LLM based on real Stripe payment conversion, plus configuration entries to surface it in the cookbook site.

• Registers the new notebook in registry.yaml
• Introduces the notebook file under examples/stripe_model_eval/
• Adds authors metadata in authors.yaml

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
registry.yaml	New entry for “Selecting a Model Based on Stripe Conversion”
examples/stripe_model_eval/selecting_a_model_based_on_stripe_conversion.ipynb	Full notebook content for the new guide
authors.yaml	Added YAML entries for two authors (third still missing)

Comments suppressed due to low confidence (3)

registry.yaml:2111

• The author shyamal-anadkat is listed here but not defined in authors.yaml. Add a matching entry in authors.yaml to avoid broken author links.

-    - shyamal-anadkat

examples/stripe_model_eval/selecting_a_model_based_on_stripe_conversion.ipynb:152

• The notebook references diagram.svg but that file isn’t included in this PR. Please add the SVG or update the path so the diagram displays correctly.

+        "<img src=\"diagram.svg\" width=\"600\">"

registry.yaml:2105

• The indentation for the new list entry doesn’t match the surrounding items (which use leading spaces before the dash). Align this entry to the same indent level so it’s recognized correctly.

+- title: Selecting a Model Based on Stripe Conversion – A Practical Eval for Startups

[shyamal-anadkat]

lgtm! thanks

[joshbickett]

Great, thanks!