# Accelerometer AI-Progress Time Series — Historical Snapshot by Date

> Accelerometer AI-Progress Time Series — Historical Snapshot by Date is a paid API for AI agents from x402-accelerometer-feed.fly.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-18).

Returns a dated snapshot of 129 AI-progress and technology time series as they stood on a specific past date, including benchmark scores, compute trends, prediction market odds, pricing, and acceleration metrics between readings.

## Facts

- Endpoint: GET https://x402-accelerometer-feed.fly.dev/ai-progress/as-of/%7Bid%7D
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-18
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/accelerometer-ai-progress-time-series-historical-snapshot-by-date-846bb447
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_pNggkdi1MHQR0d_fOaeYz

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 accelerometer-ai-progress-time-series-historical-snapshot-by-date-846bb447
```

Example prompt: Pull the Accelerometer AI-progress snapshot for July 12 2026 — I want to see all 129 time series readings as they stood on that date, including the benchmark scores, compute trends, and acceleration percentages.

## When to prefer this

Choose this endpoint when you need AI-progress data anchored to a specific historical date rather than the current moment. It is ideal for retrospective analysis, auditing what benchmarks showed at a past date, verifying prediction market odds historically, or computing acceleration between two dated snapshots. Prefer the /latest endpoint when you only need the most current readings without specifying a date.

## Known failure modes

- Snapshot date not found — if the requested date has no pre-computed snapshot, the endpoint may return a 404 or empty result
- Payment failure — if the x402 USDC payment on Base is not completed or is invalid, the request is rejected
- Date format error — malformed date string in the {id} path parameter returns a 400 error
- One or more sources unavailable — n_sources_ok may be less than n_sources if upstream data sources were unreachable at snapshot time
- Future date requested — requesting a date beyond available snapshots returns an error or empty stub

## How this service works

Readings of AI progress: dated snapshots of 129 public AI-progress and technology time series (frontier benchmark scores, compute trends, AGI prediction-market odds, model pricing, AI stocks and crypto, energy, space, robotics, biomed, research output), and the acceleration between any two readings. Paid with USDC on Base via x402.

## Output

A JSON object containing a dated snapshot of up to 129 AI-progress and technology time series, each with its latest observed value as of the requested date, its previous observation, the percentage change between them, source URL, unit, domain tag, confidence rating, signal quality, and cadence description. Also includes run metadata: snapshot_id, run_at, emitted_at, list of domains covered, and a composite note.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "properties": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "stub": false,
  "run_at": "2026-07-12T14:00:05.754191+00:00",
  "domains": [
   "agents",
   "autonomy",
   "benchmarks",
   "biomed",
   "capital",
   "compute",
   "crypto",
   "ecosystem",
   "energy",
   "industrial",
   "inference",
   "macro",
   "markets",
   "narrative",
   "patents",
   "prediction",
   "pricing",
   "research",
   "robotics",
   "science",
   "space"
  ],
  "sources": [
   {
    "id": "agents.x402_services_count",
    "url": "https://agentic.market",
    "unit": "count",
    "access": "free_api",
    "domain": "agents",
    "latest": 1779,
    "metric": "x402 pay-per-request services (agentic.market)",
    "cadence": "weekly survey, accumulating",
    "n_points": 8,
    "previous": 1525,
    "confidence": "verified",
    "first_date": "2026-04-21",
    "latest_date": "2026-07-12",
    "previous_date": "2026-07-05",
    "signal_quality": "strong",
    "delta_pct_vs_previous": 16.6557
   },
   {
    "id": "autonomy.metr_time_horizon_50",
    "url": "https://github.com/METR/cross-domain-horizon (data/external/logistic_fits/headline.csv; METR 'Measuring AI Ability to Complete Long Tasks', metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/)",
    "unit": "minutes",
    "access": "dataset_download",
    "domain": "autonomy",
    "latest": 112.230447,
    "metric": "METR frontier task-completion horizon @50% (minutes)",
    "cadence": "updated as METR re-fits new models",
    "n_points": 15,
    "previous": 54.226342,
    "confidence": "verified",
    "first_date": "2019-02-14",
    "latest_date": "2025-04-16",
    "previous_date": "2025-02-24",
    "signal_quality": "strong",
    "delta_pct_vs_previous": 106.9667
   }
  ],
  "composite": null,
  "n_sources": 129,
  "emitted_at": "2026-09-16T11:54:41+00:00",
  "snapshot_id": "2026-07-12",
  "n_sources_ok": 126,
  "composite_note": "No cross-source composite is offered. Each row is one source's latest observation as pulled at run_at, with its previous observation and the % change between them.",
  "schema_version": "0.2"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/accelerometer-ai-progress-time-series-historical-snapshot-by-date-846bb447/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-accelerometer-feed.fly.dev](https://www.zero.xyz/host/x402-accelerometer-feed.fly.dev/llms.txt)