# Animica Compute Inventory

> Animica Compute Inventory is a paid API for AI agents from animica.dev, paid per call via x402, $0.001799/call, status unknown (last checked 2026-09-15).

Returns live capacity of the Animica compute network: which GPU render kinds have active miners, inference worker availability, and the chain height at time of measurement.

## Facts

- Endpoint: POST https://animica.dev/x402/compute/inventory
- Price: $0.001799/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/animica-compute-inventory-86af0727
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_mwMh4fPXhyHEHkLyBfJeQ

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 animica-compute-inventory-86af0727 -d '<json body>'
```

Example prompt: Before I submit a video render job on Animica, check the live compute inventory — force a fresh probe — and tell me whether the video workload type has miners online and what the current chain height is.

## When to prefer this

Use this endpoint immediately before paying for any Animica render or inference job to confirm the workload type is actually serviceable. Prefer it over assuming availability or retrying failed jobs — it saves money by surfacing unclaimed-job risk before payment. Especially valuable when targeting niche render kinds like video_i2v or audio_master where miner counts may be low.

## Known failure modes

- Network node unreachable — returns available:false with a reason rather than a zero count
- Stale memo returned if fresh:false and cache hasn't expired — use fresh:true before committing payment
- Workloads array exceeds 8 items — request rejected
- Unknown workload kind specified — may return unavailable verdict with reason

## How this service works

Live capacity of the Animica compute network in one call: which GPU render kinds have miners online right now and how many, whether a registered AICF worker is serving inference, and the chain height it was measured at. Buy it BEFORE you pay for a render or an inference call, so you pick a servable kind instead of learning from a job nothing claims. Anything we could not reach reports available:false with a reason: counts are never guessed and never a zero we did not measure.

## Output

Returns per-render-kind miner counts and online status, AICF inference worker presence, the blockchain height at measurement time, and per-workload admission verdicts. Unavailable data is flagged with available:false and a reason — counts are never guessed or fabricated.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "fresh": {
   "type": "boolean",
   "description": "force a live re-probe instead of the short-lived memo (default false). Use it immediately before you commit money to a job."
  },
  "workloads": {
   "type": "array",
   "description": "up to 8 workloads to get an admission verdict for — inference, image, video, audio, or a media kind such as video_i2v or audio_master"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/animica-compute-inventory-86af0727/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from animica.dev](https://www.zero.xyz/host/animica.dev/llms.txt)