OpenAI · Ai◎ discry
Sharp
Agents read these docs at full fidelity
DISCOVERY73.7
COMPREHENSION97.7
Frontier required#3 of 51 Ai APIs · 96th percentile
AI · RANK #3 OF 51

OpenAI is Sharp to agents.

Discry independently scored how well an AI agent can discover and understand the OpenAI API from what’s public — measuring discovery and comprehension separately, not a single blended number.

Familiarity 77% · what a model knew before reading the docs

Discry your API — freeView the docs ↗

Discovery

74 / 100
OpenAPI spec288 endpointsPass
llms.txt38 described linksPass
llms-full.txt1422923 tokensPass
AGENTS.mdnot found in repoFail
.well-known/mcp.jsonnot presentFail
MCP registrynot found in probed registriesFail
robots.txt AI directivesparsed AI-bot rulesPass
Sitemapincludes docs pagesPass

Comprehension

98 / 100
Factual recall2/2 passed
Request construction2/2 passed
Absence honesty1/1 passed

See your own Discry result.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free