# Text Embedding API (768-dim)

> Text Embedding API (768-dim) is a paid API for AI agents from pearl-valium-stickers-upc.trycloudflare.com, paid per call via x402, $0.005/call, status down (last checked 2026-11-04).

Converts text strings into 768-dimensional vector embeddings for semantic similarity, search, and downstream ML tasks.

## Facts

- Endpoint: POST https://pearl-valium-stickers-upc.trycloudflare.com/v1/embed?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: down
- Last checked: 2026-11-04
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/text-embedding-api-768-dim-b705adf7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GAvwR2psr6xReQWVSlmN8

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 text-embedding-api-768-dim-b705adf7 -d '<json body>'
```

Example prompt: Embed this sentence for me using the local 768-dim model: 'The quick brown fox jumps over the lazy dog' — I need the vector to do a similarity search.

## When to prefer this

Choose this endpoint when you need 768-dimensional embeddings generated locally (privacy-preserving, no data sent to third-party APIs), particularly for RAG pipelines, semantic search indexes, or clustering tasks. Prefer this over OpenAI or Cohere embeddings when data privacy is critical, when you need consistent offline availability, or when cost per call matters at scale. The 768-dim output is compatible with most standard vector databases (Pinecone, Weaviate, Qdrant).

## Known failure modes

- Empty input string returns a zero vector or error
- Oversized input exceeding model context window may be truncated or rejected
- Transient Cloudflare tunnel downtime causes 502/503 errors
- Malformed JSON body returns 400 bad request
- Model identifier mismatch returns error if specified model is unavailable

## How this service works

Text embeddings (768-dim). Send {"input": "text"} or {"input": ["a","b"]}.

## Output

Returns an object containing one or more 768-dimensional float vectors corresponding to the input text(s), along with model name, object type, and token usage statistics. Each embedding is a dense array of 768 floating-point numbers suitable for cosine similarity or dot-product comparisons.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "array"
  },
  "model": {
   "type": "string"
  },
  "usage": {
   "type": "object"
  },
  "object": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/text-embedding-api-768-dim-b705adf7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pearl-valium-stickers-upc.trycloudflare.com](https://www.zero.xyz/host/pearl-valium-stickers-upc.trycloudflare.com/llms.txt)