# AgentUtility Embedding Similarity

> AgentUtility Embedding Similarity is a paid API for AI agents from x402.agentutility.ai, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Computes cosine similarity between two text strings using BGE-M3 embeddings via Venice AI

## Facts

- Endpoint: POST https://x402.agentutility.ai/embedding-similarity
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentutility-embedding-similarity-ff17bc15
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Q3Yz_VqVHhdeRWcrQZTWE

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 agentutility-embedding-similarity-ff17bc15 -d '<json body>'
```

Example prompt: How semantically similar are the phrases 'AI agent payments' and 'autonomous transactions'? Use BGE-M3 embeddings with 1024 dimensions and give me the similarity score.

## When to prefer this

Use this endpoint when you need a quick, cheap ($0.005 USDC), pay-per-call semantic similarity score between two text strings without hosting your own embedding infrastructure. Prefer it over general LLM comparisons when you want a deterministic numerical similarity score from a specific embedding model (BGE-M3). Ideal for ranking, deduplication, clustering, or relevance scoring tasks within agent workflows.

## Known failure modes

- Missing text_a or text_b returns 400 Bad Request
- Invalid model name returns error or falls back to default
- Payment not included or insufficient USDC triggers x402 payment required response
- Text inputs too long for model context window may be truncated or rejected
- Network timeout if Venice AI backend is unavailable

## How this service works

Paid x402 endpoints organized into product clusters. USDC-settled on Base. MCP-callable. ERC-8004 identity registry agentId 47167.

## Output

A JSON object with the similarity score (float between 0 and 1), the model used (e.g. text-embedding-bge-m3), the source provider (venice), the two input texts, and the embedding dimensions used.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "required": [
      "text_a",
      "text_b"
     ],
     "properties": {
      "model": {
       "type": "string",
       "description": "Venice embedding model. Default 'text-embedding-bge-m3'."
      },
      "text_a": {
       "type": "string",
       "description": "First text. Up to 30,000 chars."
      },
      "text_b": {
       "type": "string",
       "description": "Second text. Up to 30,000 chars."
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "model": {
       "type": "string"
      },
      "source": {
       "type": "string"
      },
      "text_a": {
       "type": "string"
      },
      "text_b": {
       "type": "string"
      },
      "dimensions": {
       "type": "integer"
      },
      "similarity": {
       "type": "number"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "text-embedding-bge-m3",
  "source": "venice",
  "text_a": "AI agent payments",
  "text_b": "Autonomous transactions",
  "dimensions": 1024,
  "similarity": 0.7842
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentutility-embedding-similarity-ff17bc15/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.agentutility.ai](https://www.zero.xyz/host/x402.agentutility.ai/llms.txt)