# Create Embeddings (ZeroClick-authenticated) — ZeroGPU

> Create Embeddings (ZeroClick-authenticated) — ZeroGPU is a paid API for AI agents from agents.zerogpu.ai, paid per call via MPP, price unknown, status unknown (last checked 2026-10-16).

Converts one or more text strings into 384-dimensional embedding vectors using lightweight sentence-transformer models (all-MiniLM-L6-v2 or BGE-small-en-v1.5), authenticated via HMAC signature.

## Facts

- Endpoint: POST https://agents.zerogpu.ai/zeroclick/v1/embeddings?utm_source=zero.xyz
- Price: price unknown
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Provider: agents.zerogpu.ai
- Website: https://agents.zerogpu.ai
- Canonical page: https://www.zero.xyz/c/agents-zerogpu-ai-create-embeddings-zeroclick-authenticated-zerogpu-4d296d1e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bY6oLzKIyS1DMa7jevpSS

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 agents-zerogpu-ai-create-embeddings-zeroclick-authenticated-zerogpu-4d296d1e -d '<json body>'
```

Example prompt: Embed the sentence 'The quick brown fox jumps over the lazy dog' using the all-minilm-l6-v2 model on ZeroGPU and give me back the vector.

## When to prefer this

Choose this endpoint when you need fast, low-cost text embeddings using compact sentence-transformer models (all-MiniLM-L6-v2 or BGE-small-en-v1.5) with OpenAI-compatible output format and HMAC-based ZeroClick authentication. Prefer it over the standard /v1/embeddings endpoint when operating in a ZeroClick orchestration context. Ideal for high-volume embedding workloads (RAG, semantic search, clustering) where small 384-dimension models provide sufficient quality at minimal token cost.

## Known failure modes

- Invalid or missing zc-signature HMAC — authentication failure, request rejected
- Unsupported model name outside the enum [all-minilm-l6-v2, bge-small-en-v1.5] — validation error
- Empty input string or empty array — schema validation error (minLength/minItems violated)
- Input text truncated silently at model's maximum token length without error
- Insufficient credits or payment failure — 402 Payment Required
- Rate limiting or overload on ZeroGPU inference network — 429 or 503 response

## How this service works

OpenAI-style Embeddings endpoint. Billed on input tokens only; `zc-usage`
reports the `prompt_tokens` from the response's `usage`.

Authenticated by verifying the `zc-signature` HMAC over the raw
request bytes; the same orchestration as `/v1/embeddings` runs behind it.


## Output

Returns an OpenAI-compatible embedding list object containing: an array of embedding objects each with its index, object type, and a 384-dimensional float vector; the resolved model ID; and a usage object reporting prompt_tokens and total_tokens (billed on input tokens only, no output tokens).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "model",
  "input"
 ],
 "properties": {
  "input": {
   "oneOf": [
    {
     "type": "string",
     "minLength": 1
    },
    {
     "type": "array",
     "items": {
      "type": "string",
      "minLength": 1
     },
     "minItems": 1
    }
   ],
   "description": "Text to embed. A single string, or an array of strings (one vector per element). Inputs are truncated at the model's max token length."
  },
  "model": {
   "enum": [
    "all-minilm-l6-v2",
    "bge-small-en-v1.5"
   ],
   "type": "string",
   "example": "all-minilm-l6-v2",
   "description": "Embedding model to use. Embedding models are routable only on this endpoint."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "index": {
      "type": "integer",
      "example": 0,
      "description": "Position of the input this vector was produced from."
     },
     "object": {
      "type": "string",
      "example": "embedding"
     },
     "embedding": {
      "type": "array",
      "items": {
       "type": "number"
      },
      "description": "The embedding vector. 384 dimensions for both models."
     }
    }
   }
  },
  "model": {
   "type": "string",
   "example": "all-MiniLM-L6-v2",
   "description": "The resolved model id."
  },
  "usage": {
   "type": "object",
   "properties": {
    "total_tokens": {
     "type": "integer",
     "example": 18
    },
    "prompt_tokens": {
     "type": "integer",
     "example": 18
    }
   },
   "description": "Embeddings are billed on input tokens only; there are no output tokens."
  },
  "object": {
   "type": "string",
   "example": "list"
  }
 },
 "description": "An OpenAI-compatible embedding list."
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-zerogpu-ai-create-embeddings-zeroclick-authenticated-zerogpu-4d296d1e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.zerogpu.ai](https://www.zero.xyz/host/agents.zerogpu.ai/llms.txt)