# dev-5090 Text Embedding API

> dev-5090 Text Embedding API is a paid API for AI agents from dev-5090-box.tailfb4c1f.ts.net, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-12).

Generates 768-dimensional vector embeddings for one or more input text strings

## Facts

- Endpoint: POST https://dev-5090-box.tailfb4c1f.ts.net/v1/embed?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/dev-5090-text-embedding-api-08585c61
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_X2FBXs4-a75k47tnkNo-f

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 dev-5090-text-embedding-api-08585c61 -d '<json body>'
```

Example prompt: Turn this sentence into a 768-dimensional embedding vector so I can store it in my vector database: 'The quick brown fox jumps over the lazy dog.'

## When to prefer this

Choose this endpoint when you need 768-dimensional dense embeddings from a self-hosted, uncensored model on private infrastructure (Tailscale network) and are comfortable with per-call micropayments via x402. Prefer this over hosted OpenAI/Cohere embeddings when privacy, censorship resistance, or cost predictability at small scale matters. Less suitable for high-throughput production workloads requiring SLA guarantees.

## Known failure modes

- Empty or missing 'input' field returns a validation error
- Input text exceeding model context window may be truncated or rejected
- Network unreachability of the Tailscale private host returns a connection timeout
- Payment of $0.005 USDC not sent or rejected causes HTTP 402 response
- Batch array with too many strings may cause OOM on the RTX 5090 GPU

## How this service works

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

## Output

Returns a 768-dimensional floating-point vector (or array of vectors for batch input) representing the semantic content of the input text, along with token usage metadata. The embeddings can be used directly for cosine similarity, nearest-neighbor search, clustering, or as features in downstream ML tasks.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "usage": {
   "type": "object"
  },
  "choices": {
   "type": "array"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/dev-5090-text-embedding-api-08585c61/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from dev-5090-box.tailfb4c1f.ts.net](https://www.zero.xyz/host/dev-5090-box.tailfb4c1f.ts.net/llms.txt)