# OpenAI — API Agent Score

> Score: 83/100 (Grade: A) | Domain: openai.com | Rubric: 1.0.0 | Checked: July 22, 2026

OpenAI scored 83/100 (A), classified "ai-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/openai)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 83/100 (A)
- Classification: ai-ready

## Category Scores

- API Design: 100/100 (A+)
- Developer Experience: 76/100 (B)
- Agent Discovery: 73/100 (B)
- Agent Understanding: 74/100 (B)
- Agent Usability: 92/100 (A+)

## Check Results

### API Design

- [pass] Machine-readable, versioned contract — Versioning declared (info.version="2.3.0") and url-versioning detected. Investigated: spec 100%, docs 100%.
- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.
- [warn] Schema coverage & depth — 7686/7729 (99%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 100%, spec 67%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 50%.
- [pass] Example coverage — Code samples in 5 language(s) across docs (top: shell, javascript, python); 2/19 pages have ≥ 2 languages on the same page. Investigated: docs 100%, sdk 100%, spec 0%.

### Developer Experience

- [pass] Quickstart present — Quickstart at https://developers.openai.com/api/docs/quickstart has a runnable sample in the .md variant (https://developers.openai.com/api/docs/quickstart.md). Investigated: docs 100%.
- [pass] Code samples in docs — Code samples in 5 language(s) across docs (top: shell, javascript, python); 2/19 pages have ≥ 2 languages on the same page. Investigated: docs 100%.
- [pass] Description completeness — 88% description completeness (target 90%+). Investigated: spec 100%, sdk 73%.
- [pass] Changelog published — changelog documented in the docs site at https://developers.openai.com/api/docs/changelog. Investigated: spec 100%, docs 100%, sdk 100%.
- [fail] Self-service developer portal — No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). Investigated: docs 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Indexed on Context7 (macpaw/openai, 587 snippets). Investigated: docs 100%, cli 100%, sdk 58%.
- [warn] llms.txt present, valid & comprehensive — No llms.txt directive found in HTML of any of 50 sampled pages. Investigated: docs 63%, sdk 0%.
- [warn] Docs reachable, not hard auth-gated — 8 of 50 sampled pages return 200 for non-existent URLs (soft 404). Investigated: docs 38%.
- [warn] Crawlable / AEO — Sitemap present (1 entries) but carries no lastmod values. Investigated: wellknown 75%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — error codes documented in the docs site at https://developers.openai.com/api/docs/guides/error-codes. Investigated: docs 100%, sdk 100%, spec 50%.
- [pass] Operation purpose clarity — 100% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [warn] Agent-navigable, token-efficient docs — 16 of 39 pages have substantive content differences between markdown and HTML (avg 36% missing). Investigated: docs 65%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 2 surfaces (spec, docs) is 8% (threshold 35% for full credit).
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [fail] Docs structured data — Neither JSON-LD nor OpenGraph/meta tags detected across 2 assessed pages (2 JS-rendered). Investigated: docs 0%.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%.
- [pass] Rate-limit signaling — rate-limit behavior documented in the docs site at https://developers.openai.com/api/docs/guides/batch. Investigated: spec 100%, docs 100%.
- [pass] Pagination documented & consistent — Pagination params detected on 65 list endpoint(s). Investigated: spec 100%, docs 100%, sdk 42%.
- [pass] Sandbox separation — sandbox documented in the docs site at https://developers.openai.com/api/docs/guides/agents/sandboxes. Investigated: spec 100%, docs 100%, sdk 100%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

OpenAI's API program excels at API design and usability fundamentals, but two areas are holding back partner and agent success: agent understanding and agent usability. Partners' AI agents lack the structured context, machine-readable docs, and runnable examples they need to integrate correctly without guesswork — and the absence of a self-service developer portal forces unnecessary friction early in the partner journey. Prioritize making your documentation machine-readable and executable first, then close the self-service onboarding gap to convert partner interest into working integrations faster.