# Fireworks — API Agent Score

> Score: 78/100 (Grade: B) | Domain: fireworks.ai | Rubric: 1.0.0 | Checked: July 24, 2026

Fireworks scored 78/100 (B), classified "partially-ready".

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

## Summary

- Overall: 78/100 (B)
- Classification: partially-ready

## Category Scores

- API Design: 59/100 (D)
- Developer Experience: 71/100 (B)
- Agent Discovery: 91/100 (A+)
- Agent Understanding: 84/100 (A)
- Agent Usability: 86/100 (A)

## Check Results

### API Design

- [warn] Schema coverage & depth — 22/284 (8%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 52%.
- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 0%.
- [fail] Security & governance hygiene — No security.txt at /.well-known/security.txt or /security.txt. Investigated: wellknown 0%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Self-service developer portal — Self-service signup at https://app.fireworks.ai/signup; no free tier or sandbox language detected. Investigated: docs 100%.
- [pass] Changelog published — Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%.
- [warn] Quickstart present — Quickstart page reachable (1 variants scanned starting at https://docs.fireworks.ai/getting-started/introduction) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%.
- [warn] Description completeness — 64/199 operations lack a description. Investigated: sdk 68%.
- [fail] Code samples in docs — No detectable code samples across 20 sampled docs pages. Investigated: docs 0%.

### Agent Discovery

- [pass] Docs reachable, not hard auth-gated — All 1 pages are publicly accessible. Investigated: docs 100%.
- [pass] Registry & SDK presence — Indexed on Context7 (websites/fireworks_ai, 5585 snippets). Investigated: docs 100%, wellknown 50%, sdk 42%, cli 0%, mcp 0%.
- [warn] llms.txt present, valid & comprehensive — No /llms-full.txt found at the candidate origins. Investigated: docs 67%, sdk 0%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.

### Agent Understanding

- [pass] Machine-readable errors (RFC 9457) — Single base error "FWError" with 6 subclasses. Investigated: sdk 100%.
- [pass] Agent-navigable, token-efficient docs — All 1 pages contain server-rendered content. Investigated: docs 100%.
- [pass] Docs structured data — JSON-LD Article markup on 19/19 assessed pages (100%) with dateModified present. Investigated: docs 100%.
- [warn] Description consistency across surfaces — Mean pairwise description similarity across 2 surfaces (docs, sdk) is 14% (threshold 35% for full credit).
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [skip] Operation purpose clarity — No surface produced evidence for this capability in this run.

### Agent Usability

- [pass] Idempotency documented — Built-in retry machinery is present (grep-derived). Investigated: sdk 100%.
- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Fireworks.ai's API program shines in agent discovery and documentation coverage, but two areas put partner and agent adoption at risk: the API design layer has security and governance gaps that block enterprise partners before they even start, and the lack of runnable, agent-ready context means AI coding agents must guess at auth patterns and request shapes rather than execute confidently. Prioritize closing the security hygiene gap first to unblock enterprise onboarding, then layer in an agent instructions file and runnable collections so partners — and the agents they rely on — can reach production workflows without friction.