# ForwardLane Embedding Similarity Search

> ForwardLane Embedding Similarity Search is a paid API for AI agents from forwardlane.pay.zeroclick.io, paid per call via x402, $0.05/call, status unknown (last checked 2026-10-12).

Performs cosine-similarity search over function embeddings using a text query, returning the most semantically similar functions ranked by vector distance.

## Facts

- Endpoint: GET https://forwardlane.pay.zeroclick.io/api/embeddings/search?utm_source=zero.xyz
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 1
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forwardlane-embedding-similarity-search-7baf0679
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WuWOeNTCTcBEpIqr8AkkE

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 forwardlane-embedding-similarity-search-7baf0679
```

Example prompt: Search the ForwardLane function index for the top 10 functions most semantically similar to 'authenticate a user with OAuth2 token' — use the text-embedding-3-small model.

## When to prefer this

Choose this endpoint when you need semantic (meaning-based) function discovery rather than keyword or name-based search. It is ideal when you have a natural language description of what a function should do and want to find the closest matches by conceptual similarity. Prefer this over text search when synonym matching and intent-based retrieval are more important than exact token matching. The domain filter makes it especially useful when scoping searches to a known functional category.

## Known failure modes

- Missing required 'q' query parameter returns a validation error
- Invalid top_k value outside 1-200 range returns a parameter error
- Unrecognized domain filter may return empty results
- Unknown embedding model name may cause a model resolution error
- Payment not included or insufficient USDC balance returns 402 Payment Required

## How this service works

Cosine-similarity search over function embeddings.

## Output

Returns a ranked list of function matches ordered by cosine similarity to the query embedding. Each result includes function identifiers, similarity scores, and associated metadata. The number of results is controlled by top_k (default 20, max 200), and results can be filtered by domain.

## 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"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "q"
     ],
     "properties": {
      "q": {
       "type": "string"
      },
      "model": {
       "type": "string",
       "default": "text-embedding-3-small"
      },
      "top_k": {
       "type": "integer",
       "default": 20,
       "maximum": 200,
       "minimum": 1
      },
      "domain": {
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/forwardlane-embedding-similarity-search-7baf0679/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from forwardlane.pay.zeroclick.io](https://www.zero.xyz/host/forwardlane.pay.zeroclick.io/llms.txt)