◎ Discry Score
groq.com
ai · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 99 (A)
Discry your API →
AI · RANK #30 OF 43

Groq is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Groq API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 64/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Partial
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Partial
llms-full.txtA full-text bundle agents can load in one request.Pass
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Fail
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 96/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Partial
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Pass
Naming consistencyConsistent, predictable naming across endpoints.Pass
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Pass

What we found

  • An agent discovering Groq via standard signals lands cleanly: robots.txt allows all crawlers (only /dashboard, /settings, /keys are blocked), a 779KB llms-full.txt plus a descriptive llms.txt expose the full doc set as markdown, and the sitemap lists every docs page.
  • Comprehension is near-flawless. Every endpoint page leads with a task-oriented purpose, examples ship in shell/Python/JS/JSON with realistic values, and a complete 'agentic loop' tool-use walkthrough lets an agent chain calls without guessing.
  • No machine-readable OpenAPI spec at standard paths: an agent wanting to auto-generate a client 404s on openapi.json/openapi.yaml and must fall back to the OpenAI-compatible spec or a community Postman collection.
  • No AGENTS.md in Groq's official repos (groq-python, groq-api-cookbook) and no .well-known/mcp.json: a coding agent working in the SDK gets README/CONTRIBUTING but no agent-specific guidance.
  • Positive surprise for self-correction: rate limits, error codes, and cursor pagination are all explicitly documented, with retry-after headers and exponential-backoff guidance, so an agent can recover from 429s without trial and error.

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Publish a downloadable OpenAPI spec at a discoverable path (e.g. console.groq.com/openapi.json). This is the single biggest score lift (discovery weight 5) and lets agents auto-generate typed clients instead of inferring from HTML.
  2. 02Add an AGENTS.md to groq-python and groq-api-cookbook with build/test/usage context (discovery weight 3, currently failing) so coding agents get first-class guidance.
  3. 03Trim llms.txt below 50KB or split out a lean API-only index. It is currently 62KB because it bundles integration-partner pages, which pushes the quality check to partial.
  4. 04Add per-error recovery steps to the errors page — e.g. for 400, name the offending parameter and its valid values — to match the already-excellent explicit 429 guidance.
  5. 05Optionally add a .well-known/mcp.json: Groq already ships remote MCP connectors (Gmail, Drive, Calendar), so advertising them is a cheap discovery signal.

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

API key (Bearer token via Authorization header)✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Execution characteristics are well documented: API-key Bearer auth, a dedicated errors page with standard HTTP codes and JSON error bodies, an explicit rate-limits page (RPM/RPD/TPM/TPD/ASH/ASD) with retry-after and exponential-backoff guidance, and cursor-based pagination (next_cursor) on list endpoints. Idempotency keys are not documented.

See your own Discry Score.

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

Discry your API — free