# Combify Compute Text Embedding

> Combify Compute Text Embedding is a paid API for AI agents from compute.combify.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-10).

Converts input text into a 1024-dimensional vector embedding (bge-m3) for semantic search, deduplication, and clustering tasks

## Facts

- Endpoint: POST https://compute.combify.app/embed?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/combify-compute-text-embedding-f3a307be
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ro-n-XTsmoBAiDXLBqaEs

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 combify-compute-text-embedding-f3a307be -d '<json body>'
```

Example prompt: Turn this paragraph into a semantic embedding vector using bge-m3 so I can compare it against my knowledge base for RAG retrieval: 'Climate change is accelerating the melting of Arctic ice sheets at an unprecedented rate.'

## When to prefer this

Choose this endpoint when you need to compare semantic meaning between texts — for building RAG retrieval pipelines, deduplicating documents, or clustering text by topic. Do not use it for question answering (use /chat), translation (use /translate), sentiment classification, image understanding, or speech transcription. Prefer this over generic embedding APIs when you need a fixed-price, pay-per-call USDC-settled embedding with bge-m3 quality in an x402-compatible workflow.

## Known failure modes

- 402 Payment Required — no valid x402 payment header provided
- Text exceeds 8000 character limit — request rejected
- Empty or missing `text` field — validation error
- Model inference timeout for very long inputs near the character limit
- Network errors reaching compute.combify.app

## How this service works

Semantic search building block: turns text into a 1024-number vector for RAG retrieval, dedup, and clustering (bge-m3), fixed price $0.005 USDC. Use this when comparing meaning between texts, not for answers (use /chat) or translation (use /translate). POST JSON body {text (required, max 8000 chars)}. Returns {embedding, dimensions}. Unpaid calls get 402; paid calls settle only on success.

## Output

Returns a JSON object containing an `embedding` field (array of 1024 floating-point numbers representing the semantic meaning of the input text) and a `dimensions` field (integer value 1024 confirming vector size). Paid at $0.005 USDC per call; unpaid calls return HTTP 402.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to embed, max 8000 chars"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/combify-compute-text-embedding-f3a307be/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from compute.combify.app](https://www.zero.xyz/host/compute.combify.app/llms.txt)