>
    Strata Copilot
    Configure Rate Limits
    Focus
    Download PDF
    Focus
    1. Home
    2. Prisma AIRS
    3. AI Gateway
    4. Add an LLM Integration
    5. Configure Rate Limits
    Download PDF
    Prisma AIRS

    Configure Rate Limits

    Table of Contents

    Configure Rate Limits

    Set per-workspace request-per-minute and request-per-day ceilings on an LLM integration to prevent runaway usage and ensure equitable access across teams.
    Where Can I Use This?What Do I Need?
    • Prisma AIRS AI Gateway (Americas region)
    • AI Gateway activated
    • LLM integration in progress or saved
    Rate limits control the volume of requests a workspace can make to an LLM integration within a given time window. They protect against application bugs or unexpected traffic spikes that could exhaust your LLM provider quota or drive unexpected costs. Rate limits apply to the number of API calls, not to token consumption — use budget limits to cap spending. When a workspace exceeds a rate limit, AI Gateway returns HTTP 429.
    1. During LLM integration setup, select the workspace row for which you want to set rate limits.
    2. In Requests Per Minute, enter the maximum number of API requests allowed per minute for this workspace on this integration.
      Leave blank to apply no per-minute limit. The provider's own rate limit still applies.
    3. In Requests Per Day, enter the maximum number of API requests allowed per calendar day (UTC) for this workspace.
      Leave blank to apply no daily limit. The daily counter resets at 00:00 UTC.
    4. Repeat for each workspace that requires a rate limit.
      When a workspace reaches its request-per-minute limit, AI Gateway immediately returns HTTP 429 (Too Many Requests) for subsequent requests until the minute window expires. When a workspace reaches its daily request limit, HTTP 429 is returned for the remainder of that calendar day. Rate limit events are recorded in the observability logs.

    © 2026 Palo Alto Networks, Inc. All rights reserved.