# Vapi — API Agent Score

> Score: 75/100 (Grade: B) | Domain: vapi.ai | Rubric: 1.0.0 | Checked: July 24, 2026

Vapi scored 75/100 (B), classified "partially-ready".

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

## Summary

- Overall: 75/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 84/100 (A)
- Developer Experience: 57/100 (D)
- Agent Discovery: 100/100 (A+)
- Agent Understanding: 79/100 (B)
- Agent Usability: 58/100 (D)

## Check Results

### API Design

- [pass] Auth declared & discoverable — Authentication required (global or on every operation). Investigated: spec 100%, docs 100%.
- [warn] Machine-readable, versioned contract — info.version="1.0" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%.
- [pass] Security & governance hygiene — No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 0%.
- [warn] Schema coverage & depth — Max schema nesting depth: 16 (≥15 = deep). Investigated: spec 50%.
- [pass] Example coverage — Code samples present on 3/20 pages across 1 language(s); broader multi-language coverage missing. Investigated: docs 100%, spec 0%.

### Developer Experience

- [pass] Code samples in docs — Code samples present on 3/20 pages across 1 language(s); broader multi-language coverage missing. Investigated: docs 100%.
- [pass] Changelog published — Newest official SDK activity 1 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%.
- [warn] Quickstart present — Quickstart page reachable (1 variants scanned starting at https://docs.vapi.ai/quickstart) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%.
- [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%.
- [fail] Description completeness — 47% description completeness. Investigated: spec 0%.

### Agent Discovery

- [pass] Registry & SDK presence — Official CLI at VapiAI/cli with published releases (installable). Investigated: cli 100%, docs 0%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.
- [skip] llms.txt present, valid & comprehensive — No surface produced evidence for this capability in this run.
- [skip] Docs reachable, not hard auth-gated — No surface produced evidence for this capability in this run.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Only 2 distinct 4xx/5xx codes documented (plus 0 "default" catch-all responses). Investigated: spec 100%, docs 100%.
- [pass] Operation purpose clarity — 92% of operations have a clear summary + operationId an agent can select on. Investigated: spec 100%.
- [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%.
- [skip] Agent-navigable, token-efficient docs — No surface produced evidence for this capability in this run.
- [skip] Description consistency across surfaces — Only 0 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Rate-limit signaling — rate-limit behavior documented in the docs site at https://docs.vapi.ai/providers/model/azure-openai. Investigated: spec 100%, docs 100%.
- [pass] Pagination documented & consistent — Pagination params detected on 17 list endpoint(s). Investigated: spec 100%, docs 100%.
- [fail] Idempotency documented — 0% of mutating operations document idempotency. Investigated: spec 0%, docs 0%.
- [fail] Sandbox separation — No sandbox/test server declared across 1 server entries; no test-key prefixes documented. Investigated: spec 0%, docs 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.

## Executive Summary

Vapi's API design is a genuine strength — the contract is machine-readable and schemas are well-typed, giving partners a solid foundation to build on. The critical gaps are in developer experience and agent usability: partners currently lack a self-service portal with complete endpoint descriptions, a sandbox to safely explore the API, and runnable collections that agents can use as executable context. Closing these gaps should be the top priority, followed by adding the agent-specific context files and structured data that AI coding tools need to understand and work with Vapi's API without manual interpretation.