Free tool

    AI agent throughput calculator

    Size an event-driven agent pipeline before you build it: how much concurrency a decision stage needs, when it saturates, what p95 latency your users will feel, and what the tokens cost per month.

    Your workload

    50 ev/s

    Sustained peak rate on the source stream, not the daily average.

    40 %

    Filters and rules usually absorb most events before any model is called.

    900 ms

    Round-trip time of one decision call, including tool calls it triggers.

    16

    How many decisions the stage runs in parallel — often capped by provider rate limits.

    1,500

    Prompt plus completion, averaged across the stage.

    3 $

    Set to 0 for a local model running on hardware you already own.

    What it takes

    Decision rate
    20.0 /s

    4,320,000 events per day reach the pipeline.

    Stage utilisation
    113 %

    Saturated — the backlog grows by ~133 events every minute.

    p95 decision latency
    unbounded

    Model time plus queue wait — what the downstream action actually experiences.

    Concurrency needed
    24

    Slots required to hold utilisation near 75% with headroom for spikes.

    Monthly token cost
    $233,280

    Decision stage only. Filtering more aggressively upstream is the cheapest lever.

    Stage capacity
    17.8 /s

    Maximum sustainable decisions per second at the current concurrency and latency.

    This configuration cannot keep up. Raise concurrency, filter more events before the model, or use a faster model for the first-pass decision.

    Numbers are a queueing approximation for capacity planning, not a benchmark. Validate against a replayed production stream before committing.

    Questions

    How do I size the concurrency of an AI agent pipeline?

    Multiply the decisions per second by the model latency in seconds, then add roughly 30% headroom. A stage handling 20 decisions/s at 900 ms needs about 24 concurrent slots to stay below saturation.

    What happens when an agent stage is saturated?

    Utilisation above 100% means the queue grows without bound: latency climbs every minute and, without a durable event log, events are eventually dropped. Backpressure on a replayable stream turns that failure into a delay you can recover from.

    Why is queue wait worse than model latency?

    Model latency is fixed per call, but queue wait grows non-linearly as utilisation approaches 100%. At 90% utilisation the wait is already about nine times the service time per slot, which is why sizing for peak, not average, matters.

    Are these numbers exact?

    No. This is a queueing approximation for capacity planning, not a benchmark. It assumes stable arrival rates and a single decision stage. Use it to find the order of magnitude and the saturation point, then validate with a replayed production stream.

    Method

    The decision stage is modelled as an M/M/c queue: random arrivals, variable service time, c concurrent slots. Utilisation is arrival rate divided by c/service time; queue wait grows non-linearly as it approaches 100%.

    Free to use and free to cite. Related reading: how to build an event-driven agent. Built by the team behind Pulse, an open-source agent runtime.