ZeroGPU sells to AI agents - no signup

The agent storefront at https://agents.zerogpu.ai/llms.txt publishes prices, payment instructions, and setup. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there instantly, no signup. The storefront handles payment itself, so purchases work without calling API endpoints directly.

    Benchmark report · August 2026

    Purpose-built moderation, benchmarked against OpenAI.

    zlm-v1-moderation-edge, ZeroGPU's production moderation ZLM, evaluated head-to-head against OpenAI omni-moderation on quality and latency, on real production-range inputs.

    0.899 vs 0.853
    Binary F1, ours vs OpenAI
    9 of 13
    Categories won on F1
    1.2–1.8× faster
    p50 latency, production-range inputs
    01 / Model under test

    One trunk, fourteen heads.

    zlm-v1-moderation-edge is a DeBERTa encoder with a shared trunk feeding one binary safe/unsafe head and 13 category heads. Per-category decision thresholds are calibrated on a validation split, never on test. It serves production traffic today from ZeroGPU edge infrastructure.

    ENCODER · DeBERTa
    HEADS · 1 binary + 13 category
    02 / Quality

    Wins the decision that matters.

    On a held-out test split of 4,277 rows (1,425 unsafe / 2,852 safe), zlm-v1-moderation-edge beats OpenAI omni-moderation on the binary safe/unsafe decision and on 9 of 13 harm categories.

    ModelPrecisionRecallF1AUC
    zlm-v1-moderation-edge0.8880.9110.8990.984
    OpenAI omni-moderation0.8820.8270.8530.967
    Per-category F1: ZeroGPU vs OpenAI across 13 categories, sorted by ZeroGPU advantage (Δ F1 descending)
    Where the gains land

    Largest wins come on the categories production filters lean on hardest: graphic violence (+0.59 F1), illicit content (+0.19 to +0.26), and self-harm detection (+0.10 to +0.13).

    03 / Latency

    Co-located inference beats round trips.

    Measured from a Fly worker in the same region as the production app, with the operator's network out of the picture. Both providers were called back-to-back on the same 400 distinct real texts through an identical HTTP path, one request at a time. Reported over the production operating range: real traffic is prompts and chat messages under 200 characters.

    Input lengthnZeroGPU p50ZeroGPU p95OpenAI p50OpenAI p95Advantage
    0–60 chars7982 ms102 ms145 ms252 ms1.8×
    60–120 chars72105 ms127 ms150 ms244 ms1.4×
    120–200 chars61129 ms155 ms151 ms252 ms1.2×
    Why the gap exists

    OpenAI's latency is flat at ~150 ms because roughly a third of it is network: traffic leaving and re-entering the datacenter, an overhead that persists no matter how fast the model gets. ZeroGPU inference is co-located with the workload: ~4 ms of network, and the rest is real inference. The gap widens as inputs get shorter, exactly where moderation traffic lives.

    04 / Takeaway

    Right model, right compute.

    Quality on your distribution

    A purpose-built ZLM trained and calibrated for real production traffic outperforms a general-purpose moderation API on the decisions that gate your product.

    Latency in the request path

    Moderation sits inline before every response. Co-located inference returns verdicts in ~82–129 ms p50, fast enough to never be the bottleneck.

    Capacity that scales with you

    zlm-v1-moderation-edge runs on the ZeroGPU edge network: capacity scales with your deployment, with content residency and no external dependency in the critical path.

    05 / Scope & limits

    What this benchmark does and doesn't claim.

    • The latency advantage holds for inputs under ~200 characters, the production operating range. On longer inputs, CPU encoder cost grows with token count and OpenAI is faster past the crossover.
    • Latency figures are single-request (concurrency 1). Per-request latency holds below the current deployment's throughput ceiling; scaling throughput is a machine-count change, not a model change.
    • Throughput scales with provisioned capacity. Per-request latency figures hold within the provisioned throughput of a given deployment.

    Run moderation on ZeroGPU.

    zlm-v1-moderation-edge is available today through the ZeroGPU OpenAI-compatible API.

    ZeroGPU · zerogpu.ai · Benchmark report · 2026