# Vektorwerk Similarity Scoring

> Vektorwerk Similarity Scoring is a paid API for AI agents from vektor.netzhandwerker.de, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-13).

Embeds a query and up to 64 candidate texts locally, then returns cosine similarity scores and stable descending ranks for each candidate.

## Facts

- Endpoint: POST https://vektor.netzhandwerker.de/similarity
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vektorwerk-similarity-scoring-f4587dde
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_VJHBIaEkqEzEtFbqdd_Y8

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 vektorwerk-similarity-scoring-f4587dde -d '<json body>'
```

Example prompt: Score these 5 FAQ answers by how well they match the question 'How do I reset my password?' and return them ranked best to worst — use the bge_m3 model.

## When to prefer this

Prefer this endpoint when you need fast, local semantic similarity scoring with stable ranks across up to 64 candidates per query — especially useful for RAG reranking, FAQ matching, or deduplication pipelines where you want cosine scores rather than just ordering. Choose this over cloud embedding APIs when latency, privacy, or per-token cost is a concern, and when nomic or bge_m3 embedding quality is sufficient for your use case.

## Known failure modes

- More than 64 candidates submitted — request rejected with validation error
- Empty candidates array — rejected due to minItems:1 constraint
- Invalid model value outside the enum [nomic, bge_m3] — returns error
- Query or candidates too long for the model's context window — truncation or error
- Local Ollama runtime unavailable — service returns 500 or timeout
- Payment not provided or insufficient — x402 payment required response

## How this service works

Embeds one query and up to 64 candidates locally, then returns cosine scores and stable descending ranks.

## Output

Returns a ranked list of candidates ordered by descending cosine similarity score, including the numeric cosine score and stable integer rank for each candidate, computed from locally-run embeddings using the selected model (nomic or bge_m3).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "enum": [
    "nomic",
    "bge_m3"
   ],
   "type": "string",
   "default": "nomic"
  },
  "query": {
   "type": "string"
  },
  "candidates": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 64,
   "minItems": 1
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vektorwerk-similarity-scoring-f4587dde/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from vektor.netzhandwerker.de](https://www.zero.xyz/host/vektor.netzhandwerker.de/llms.txt)