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.

    Independent benchmark · 784 held-out URLs · GPT-5.5 gold standard

    Classify any domain into IAB categories —
    more accurate than a frontier LLM, ~50× faster

    ZeroGPU's Domain Classification model reads nothing but the domain — e.g. espn.com — and returns standard IAB content categories. On a held-out, independently-labelled benchmark it is more accurate than GPT-5.4 Nano while running about ~50× faster.

    More accurate than GPT-5.4 Nano
    0.385
    content F1 vs 0.353 — +0.032 (+9%)
    Faster per URL
    ~50×
    ~36 ms vs ~1,900 ms median
    Higher precision
    0.425
    vs 0.333 — far fewer wrong guesses
    Hallucinated labels
    0
    can only emit valid IAB categories

    01What the model does

    A purpose-built classifier for high-volume adtech: it turns a raw domain into structured IAB content categories, topics, keywords, and intent signals — from the domain alone.

    Domain in, IAB out

    Input is just the domain (no page fetch, no crawl) — up to ~10× smaller payload than page-level classification. Ideal for dead, parked, or un-crawlable domains where there is no page to read.

    Built for the bidstream

    Low-latency, high-volume by design — bidstream enrichment, contextual targeting, brand-safety screening, and domain-level intelligence at ad-auction speed.

    Standards & integration

    Structured IAB 1.0 and IAB 2.2 outputs through ZeroGPU's OpenAI-compatible API. Supports batch processing; additional IAB tags available on request.

    02How this benchmark was measured

    A like-for-like, bias-free comparison: identical inputs, a stronger independent referee for ground truth, and the same scoring for both systems.

    1
    784 held-out URLs

    Real web addresses the model never saw in training, spanning the full breadth of IAB tier-1 categories (technology, finance, shopping, sports, health, travel, education, and more).

    2
    A stronger, neutral referee

    Every URL's correct labels were set independently by GPT-5.5 — a larger, stronger model than either system under test. It did not produce the model's training labels, so it cannot favour it.

    3
    Same task, same score

    The baseline, GPT-5.4 Nano, was prompted to do the identical URL→IAB task from the same sparse input. Both systems are scored on content micro-F1 against the gold labels.

    03Accuracy — and the shape of the win

    On the 784-URL gold benchmark the model reaches 0.385 F1 vs GPT-5.4 Nano's 0.353. The win is precision-driven: when it assigns a category it is right far more often (0.425 vs 0.333), at essentially the same recall — so downstream targeting and brand-safety decisions carry less noise.

    Precision — how often a predicted category is correctZeroGPU 0.425 · GPT-5.4 Nano 0.333
    ZeroGPU
    GPT-5.4 Nano
    Recall — how many correct categories are foundZeroGPU 0.351 · GPT-5.4 Nano 0.374
    ZeroGPU
    GPT-5.4 Nano
    F1 — the balance of the two (the headline metric)ZeroGPU 0.385 · GPT-5.4 Nano 0.353
    ZeroGPU
    GPT-5.4 Nano

    Bars scaled to 0.50. ZeroGPU leads on precision and F1; recall is a near-tie (0.351 vs 0.374). Net: +0.032 F1 (+9%) over the frontier baseline.

    04Where it wins, by content area

    Broken down by IAB tier-1 category, the model beats GPT-5.4 Nano in 18 of 26 well-populated categories — and the wins are largest exactly where contextual targeting spends the most.

    Biggest wins
    ShoppingTechnologyBusiness & FinanceSportsHealthy LivingMovies

    High-value contextual segments — shopping, technology, business & finance, sports, healthy living, and movies.

    Where it trails
    Events & AttractionsReligion & SpiritualityMedical Health

    Small, ambiguous, or naming-driven categories where a bare domain under-determines the topic and the LLM's broad world knowledge helps — the natural next targets for additional training data.

    05Why it's state-of-the-art for this task

    1
    The right backbone

    Built on ModernBERT, the strongest current compact text encoder — newer data, longer context, more efficient attention. On short, keyword-like inputs (exactly what a URL is) it extracts far more signal than older small encoders.

    2
    A stronger teacher

    Trained on ~1 million domains labelled by a capable LLM that could see the live page at labelling time. It distils that page-aware knowledge into the URL string — so it reproduces page-level judgments from the domain alone.

    3
    Confidence calibration

    A tuned per-decision confidence threshold means it commits only to categories it is sure of. That single step lifted precision from ~0.26 to ~0.42 — turning a near-tie into a clear win.

    07Speed, reliability & input

    A bidstream classifier must be fast, well-formed, and tiny to call. The model answers in tens of milliseconds, never invents a label, and takes only the domain.

    Median latency per URL
    ZeroGPU
    ~36 ms
    GPT-5.4 Nano
    ~1,900 ms

    ~50× faster — tens of milliseconds vs ~2 seconds per URL.

    Reliability & input
    0
    off-taxonomy / hallucinated labels — only valid IAB categories
    Classify a domain — the entire request
    curl https://api.zerogpu.ai/v1/responses \ -H 'content-type: application/json' \ -H 'x-api-key: zgpu-api-••••••••••••' \ -H 'x-project-id: ••••••••-••••-••••' \ -d '{ "input": "indeed.com", "model": "zlm-v1-iab-domain-classifier" }'

    No page fetch, no system prompt, no taxonomy in the request — send a domain, get structured IAB categories back. Batch processing supported for high-volume pipelines.

    Run details

    TaskURL-only IAB content classification (domain in → IAB content categories out)
    Test set784 held-out URLs, never seen in training, across IAB tier-1 categories
    Gold standardGPT-5.5 — independent referee; did not produce the model's training labels
    BaselineGPT-5.4 Nano, prompted on the identical URL→IAB task
    Metriccontent micro-F1 (precision / recall balance) — same scoring for both
    ResultF1 0.385 vs 0.353 (+0.032, +9%) · precision 0.425 vs 0.333 · recall 0.351 vs 0.374
    Latency~36 ms vs ~1,900 ms median per URL (~50× faster)
    ModelZeroGPU Domain Classification (zlm-v1-iab-domain-classifier) — ModernBERT backbone, ~1 million-domain page-aware distillation, calibrated
    ZeroGPU