# Vektorwerk Text Embedding

> Vektorwerk Text Embedding is a paid API for AI agents from vektor.netzhandwerker.de, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Embeds up to 32 texts locally using Ollama (nomic or bge-m3 model), returning dense vector representations with explicit model name and dimensions — no external paid API involved.

## Facts

- Endpoint: POST https://vektor.netzhandwerker.de/embed
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vektorwerk-text-embedding-be3d80cb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CpOT_6dXfV0yfdr8S4VmW

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-text-embedding-be3d80cb -d '<json body>'
```

Example prompt: Embed these 3 product descriptions using the nomic model so I can store them as vectors: 'wireless noise-cancelling headphones', 'over-ear studio monitor headphones', 'true wireless earbuds with ANC'.

## When to prefer this

Choose this endpoint when you need text embeddings without incurring OpenAI or Cohere API costs, when you want explicit model metadata (name + dimensions) in the response, or when batching up to 32 texts at once. Particularly suitable for self-sovereignty use cases, local-first RAG pipelines, or multilingual embedding needs via bge-m3. Prefer over cloud embedding APIs when privacy, cost-zero third-party calls, or Ollama-compatible model outputs are priorities.

## Known failure modes

- Exceeding 32 texts in the texts array returns a validation error
- Supplying an invalid model value (not 'nomic' or 'bge_m3') returns a schema error
- Empty texts array (minItems:1 violated) returns a validation error
- Ollama runtime unavailability on the server causes a 5xx error
- Very long individual texts may time out or exceed model context windows

## How this service works

Embeds up to 32 texts on the local Ollama runtime. Returns explicit model and dimensions; no paid third-party API is called.

## Output

Returns an array of embedding vectors (one per input text), along with the model name used and the dimensionality of the vectors, enabling immediate downstream use in vector stores or similarity computations.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string"
  },
  "model": {
   "enum": [
    "nomic",
    "bge_m3"
   ],
   "type": "string",
   "default": "nomic"
  },
  "texts": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 32,
   "minItems": 1
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vektorwerk-text-embedding-be3d80cb/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)