specification: API Commons Rate Limits specificationVersion: '0.1' schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/RateLimits provider: PromptArmor providerId: prompt-armor created: '2026-06-20' modified: '2026-06-20' reconciled: false tags: - AI - LLM - Security - Prompt Injection - Threat Detection - Rate Limiting - Quotas - Throttling description: >- PromptArmor's detection API is marketed as returning verdicts in real time, faster than the LLM completion it protects. PromptArmor does not publicly document specific rate limits, quotas, or throttling thresholds for its Content Check and Analyze endpoints; limits are presumed to be governed by per-customer enterprise agreements. Specific values are not reconciled in this artifact. notes: >- No public rate-limit documentation is available. Confirm any per-account RPS, RPM, or concurrency limits and the throttling response code directly with PromptArmor during reconciliation. The 429 status below is the conventional throttling code and is assumed, not confirmed in PromptArmor's public docs. sources: - https://www.promptarmor.com/ - https://promptarmor.readme.io/reference/basics-of-promptarmor-architecture responseCodes: throttled: 429 limits: - name: Requests Per Account scope: account metric: requests limit: see provider documentation notes: >- Not publicly documented; governed by enterprise agreement. PromptArmor markets low-latency real-time verdicts but does not publish a request cap. - name: Concurrency scope: account metric: concurrent_requests limit: see provider documentation notes: Not publicly documented. policies: - name: Enterprise Negotiated Limits description: Throughput is presumed negotiated per enterprise contract rather than fixed public tiers. - name: Backoff Strategy description: Clients should implement exponential backoff with jitter and honor any Retry-After header on throttling. maintainers: - FN: Kin Lane email: kin@apievangelist.com