# AiSpace Embeddings API

> AiSpace Embeddings API is a paid API for AI agents from x402.aispace.bot, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Generates vector embeddings for text input using Venice.ai-powered models via a privacy-focused API

## Facts

- Endpoint: POST https://x402.aispace.bot/api/v1/embeddings?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/aispace-embeddings-api-3c060240
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Zuxo2Ej6sBpkkwS1brGBO

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 aispace-embeddings-api-3c060240 -d '<json body>'
```

Example prompt: Can you generate an embedding vector for the text 'The quick brown fox jumps over the lazy dog' using AiSpace's embeddings API with the default model?

## When to prefer this

Choose this endpoint when you need privacy-preserving text embeddings where data does not leave the device/local context, and you want a Venice.ai-backed model accessed via x402 micropayment. Prefer this over OpenAI or Cohere embeddings if privacy is a hard requirement or if you are operating in a crypto-native/x402 payment environment.

## Known failure modes

- Missing required 'input' field returns a validation error
- Invalid or unsupported model name may return an error or fallback behavior
- Malformed query parameters cause request failure
- Insufficient USDC balance (x402 payment failure) blocks the request
- Rate limiting if too many requests are made in quick succession

## How this service works

Text embeddings on Venice models for retrieval, RAG, and semantic search, paid per request in USDC on Base via x402, no API key. Resolve a model id from GET /api/v1/models?type=embedding.

## Output

Returns a JSON object with an 'ok' boolean field indicating success; the actual embedding vector data would be returned alongside it. The response confirms the embedding was computed and returns the numerical vector representation of the input text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "description": "String or array of strings to embed."
  },
  "model": {
   "type": "string",
   "description": "Venice embedding model id. See GET /api/v1/models?type=embedding (e.g. text-embedding-bge-m3, gemini-embedding-2-preview)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": [
   {
    "index": 0,
    "object": "embedding",
    "embedding": [
     -0.05365830659866333
    ]
   }
  ],
  "model": "text-embedding-bge-m3",
  "usage": {
   "total_tokens": 3,
   "prompt_tokens": 3
  },
  "object": "list"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/aispace-embeddings-api-3c060240/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.aispace.bot](https://www.zero.xyz/host/x402.aispace.bot/llms.txt)