# Multi-Touch Marketing Attribution

> Multi-Touch Marketing Attribution is a paid API for AI agents from payai.agentstools.dev, paid per call via x402, $0.03/call, status unknown (last checked 2026-09-15).

Computes per-channel credit across five attribution models simultaneously (first-touch, last-touch, linear, time-decay, position-based) for a set of conversion paths, returning a side-by-side comparison.

## Facts

- Endpoint: POST https://payai.agentstools.dev/marketing/attribution
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/multi-touch-marketing-attribution-00c94ac4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_KOtQJThGOgcdKcz24WNNI

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 multi-touch-marketing-attribution-00c94ac4 -d '<json body>'
```

Example prompt: Run multi-touch attribution on these two customer journeys: journey 1 goes Google → Facebook → Email with 1 conversion, and journey 2 goes Organic → Paid Search → Direct with 0.5 conversions — give me all five models (first-touch, last-touch, linear, time-decay, position-based) side by side using a 7-day time-decay half-life.

## When to prefer this

Choose this endpoint when you need to compare multiple attribution models simultaneously in a single call rather than running separate models one at a time. It is ideal for marketing analysts who want a neutral, model-agnostic view of channel credit without committing to a single methodology. Prefer it over single-model attribution tools when the goal is to surface disagreements between models (e.g., first-touch vs. time-decay) to inform budget decisions. Since it is pure computation over submitted data with no external data fetching, it is reliable and deterministic given the same inputs.

## Known failure modes

- Missing required 'paths' field returns validation error
- Invalid path structure (missing channel touches) causes computation failure
- Non-numeric conversions weight or days_before values produce schema rejection
- Empty paths array may return zero-credit results or error
- Extremely large path arrays may hit timeout or payload limits
- Invalid halflife_days value (zero or negative) may cause division error in time-decay model

## How this service works

Multi-touch attribution over conversion paths, five models at once: first-touch, last-touch, linear, time-decay, and position-based. Returns per-channel credit for each model plus a comparison. Pure computation over your inputs.

## Output

Returns per-channel credit scores for each of the five attribution models (first-touch, last-touch, linear, time-decay, position-based) across all input conversion paths, plus a side-by-side comparison summary showing how credit allocation differs across models.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "paths": {
   "type": "array",
   "items": {
    "type": "object"
   },
   "description": "Conversion journeys; each has a path array of channel touches and optional conversions weight and days_before array"
  },
  "halflife_days": {
   "type": "number",
   "description": "Half-life in days for time-decay, default 7"
  },
  "default_spacing_days": {
   "type": "number",
   "description": "Assumed days between touches when no timestamps are supplied, default 1"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/multi-touch-marketing-attribution-00c94ac4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from payai.agentstools.dev](https://www.zero.xyz/host/payai.agentstools.dev/llms.txt)