# OneShot Agent API – Benchmark Tool > OneShot Agent API – Benchmark Tool is a paid API for AI agents from win.oneshotagent.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-19). Computes percentile rankings and distribution statistics for a named data attribute, placing a key entity or numeric value within a filtered peer set. ## Facts - Endpoint: POST https://win.oneshotagent.com/v1/tools/benchmark?utm_source=zero.xyz - Price: $0.02/call - Payment: x402 - Status: unknown - Last checked: 2026-10-19 - Activations on Zero: 0 - Tags: x402 - Canonical page: https://www.zero.xyz/c/oneshot-agent-api-benchmark-tool-95fdabce - Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AVv48flz3tPKZ9jQT9Ksg Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently. ## How to call it through Zero Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`): ```sh zero fetch --capability oneshot-agent-api-benchmark-tool-95fdabce -d '' ``` Example prompt: How does a 2019 Toyota Camry with 37 total vehicle complaints rank among all 2019 model-year vehicles in the U.S.? Give me its percentile, median, and the p25/p75 range for that peer group. ## When to prefer this Use this endpoint when you need to understand where a specific entity or raw value sits within a distribution of peers — e.g. ranking a vehicle, company, or data point against a filtered cohort. Prefer it over raw data lookups when the goal is comparative context (percentile, quartiles) rather than absolute values. It is uniquely suited for agentic workflows that require benchmarking without a separate analytics backend, paid per-call in USDC with no API key required. ## Known failure modes - Invalid attribute name returns an error — only attributes declared as supporting Benchmark are valid - Unknown entity key returns null or error if the key doesn't exist in the dataset - Missing both key and value causes a validation error — exactly one must be provided - Providing both key and value simultaneously is rejected - Peer filter fields not supported by the data tool cause an error - Unsupported field name for the chosen attribute returns an error - Payment failure via x402 (insufficient USDC balance) blocks the call before execution ## How this service works Tools, payments, and compute orchestration for autonomous AI agents. ## Authentication - **`x402Payment`** — paid tool endpoints use the [x402 payment protocol](https://x402.io). First call returns `402 Payment Required` with a quote; sign and resend the request with `payment-signature: ` and `X-Quote-ID: `. - **`agentId`** — free read-only endpoints accept `X-Agent-ID: ` (0x… address). - **`soulKey`** — soul marketplace seller dashboard uses `Authorization: Bearer soul_…` (issued by `POST /v1/soul/register`). - **`acpBearer`** — Stripe ACP checkout sessions use a separate bearer token plus the `API-Version: 2026-01-30` header. ## Async tools & polling Most tool endpoints return `202 Accepted` with `{ request_id, tool, status }`. Poll `GET /v1/requests/{id}` (with the same `X-Agent-ID`) to retrieve the final result. A WebSocket fallback is available at `wss:///v1/requests/subscribe`. ## Pricing See [docs.oneshotagent.com/pricing](https://docs.oneshotagent.com/pricing) for the full table. Per-call prices for this environment: | Tool | Cost | |---|---| | Web search | $0.001 | | Web read | $0.002 | | Research | $0.01 | | Person profile | $0.005 | | Person email status | $0.001 | | Person dossier | $0.10 | | Person social accounts | $0.50 | | Business search | $0.01 | | Commerce search | $0.002 | | LinkedIn history sync | $0.02 per bounded run | | LinkedIn reply | $0.02 per message | | LinkedIn message to a connection | $0.02 per message | | LinkedIn profile view | $0.01 per view | | LinkedIn post reaction | $0.01 per reaction | | Email send | quote-based; service fee from $0.005 per send | | SMS send | $0.0035 per segment per recipient | | Voice call | $0.35/minute + $5.00 number registration on the first call | | Browser task | quote-based; minimum $0.005 | | Website build | quote-based; from $1.00 | | Compute goal | quote-based; minimum budget $1.00 + 20% platform fee | ## Error format `{ "error": "", "message": "", "details": }`. Validation errors include a `details` field with the failing field paths. ## Output Returns a JSON object containing the percentile of the queried entity or value within its peer set, along with full distribution statistics: min, max, median, p25, p75, count, coverage description, as-of date, the field and attribute benchmarked, and the peer filters applied. ## Request schema (JSON Schema) ```json { "type": "object", "properties": { "key": { "type": "string", "description": "Entity key of an entity in the peer set, to place its value. Give at most one of key and value" }, "field": { "type": "string", "description": "Numeric field to compare, one the data tool declares for Benchmark, e.g. total" }, "peers": { "type": "object", "description": "Filters that define the peer set: fields the data tool declares for grouping, e.g. {\"model_year\": 2019}" }, "value": { "type": "number", "description": "A value to place in the distribution. Give at most one of key and value" }, "source": { "type": "string", "description": "Source to read when the attribute has several" }, "attribute": { "type": "string", "description": "Name of a data tool whose facts can be benchmarked, e.g. vehicle_complaints" } } } ``` ## Response schema (JSON Schema) ```json { "type": "json", "example": { "max": 311, "min": 0, "p25": 6, "p75": 52.5, "as_of": "2026-09-30T12:00:00.000Z", "count": 42, "field": "total", "peers": { "model_year": 2019 }, "value": 37, "median": 19, "source": null, "coverage": "Vehicles sold in the United States", "attribute": "vehicle_complaints", "percentile": 66.67, "population": "looked_up", "population_detail": { "scope": null, "state": null, "reason": "the peers are only entities that someone has looked up", "dataset": null, "published_at": null, "source_version": null, "historical_start": null } } } ``` ## More - Live health (JSON, refreshed every minute): https://www.zero.xyz/c/oneshot-agent-api-benchmark-tool-95fdabce/health.json - [Zero catalog index](https://www.zero.xyz/llms.txt) - [Other services from win.oneshotagent.com](https://www.zero.xyz/host/win.oneshotagent.com/llms.txt)