Use when you need image embeddings or text embeddings in one 2048-dimension spac
Use when you need image embeddings or text embeddings in one 2048-dimension space for retrieval, RAG, semantic search, clustering, or dedup (Qwen3-VL-Embedding-2B, OpenAI-compatible). Batch up to 256 items per call, served 32 at a time. An x402 call is $0.002 when the request includes images, $0.001 for text-only. USDC on Base. 400 is a bad body, 413 is over 48 MiB, 429 means busy (Retry-After).
Answeringour last check, 2026-10-21
1 of 1checks answered this week
1445 msmedian answer time
$0.002listed price per call
$0.002price it asked us
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
POST https://watt.area21.io/v1/embeddings
| Category | Image and media |
|---|---|
| Provider host | watt.area21.io |
| Networks | eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 3 from 2 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-10-21 | valid payment request | 402 | $0.002 | 1445 ms |
Example input (from the provider)
{
"body": {
"input": [
{
"image": "https://example.com/bicycle.jpg",
"text": "a red bicycle"
}
],
"instruction": "Retrieve pictures of this subject.",
"model": "qwen3-vl-embedding-2b"
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"dimensions": {
"description": "Matryoshka length of each vector, from 64 to 2048. Default 2048.",
"maximum": 2048,
"minimum": 64,
"type": "integer"
},
"encoding_format": {
"description": "float (default) or base64.",
"enum": [
"float",
"base64"
],
"type": "string"
},
"input": {
"description": "One item, or a list of up to 256, batched 32 at a time. An item is text, an image, or both. An image is a data URL, base64, or a public https URL. An x402 call is $0.002 when the request includes images, $0.001 for text-only.",
"oneOf": [
{
"description": "A single text to embed.",
"type": "string"
},
{
"description": "Up to 256 items in one call.",
"items": {
"description": "Text, an image, or both, embedded as one vector.",
"oneOf": [
{
"description": "Text to embed.",
"type": "string"
},
{
"description": "Text, an image, or both.",
"properties": {
"image": {
"description": "Image as a data URL, base64, or public https URL. An x402 call is $0.002 when the request includes images, $0.001 for text-only.",
"type": "string"
},
"text": {
"description": "Text paired with the image, or text alone.",
"type": "string"
}
},
"type": "object"
}
]
},
"maxItems": 256,
"type": "array"
}
]
},
"instruction": {
"description": "What the vectors are for. The model is instruction-aware; set this for retrieval.",
"type": "string"
},
"model": {
"description": "Embedding model id. qwen3-vl-embedding-2b when omitted.",
"type": "string"
}
},
"required": [
"input"
],
"type": "object"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"headers": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"method": {
"enum": [
"POST",
"PUT",
"PATCH"
],
"type": "string"
},
"queryParams": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"errors": {
"description": "Documented errors: 400 invalid body, 413 body too large, 429 rate limit with Retry-After.",
"items": {
"properties": {
"description": {
"description": "When this status is returned.",
"type": "string"
},
"status": {
"description": "HTTP status.",
"type": "integer"
}
},
"required": [
"status",
"description"
],
"type": "object"
},
"type": "array"
},
"example": {
"properties": {
"data": {
"description": "One vector per input item, in order.",
"items": {
"properties": {
"embedding": {
"description": "The vector: an array of floats, or base64 when encoding_format is base64. 2048 dimensions unless dimensions says otherwise.",
"oneOf": [
{
"description": "Float vector.",
"items": {
"type": "number"
},
"type": "array"
},
{
"description": "Base64 vector.",
"type": "string"
}
]
},
"index": {
"description": "Position in the input, starting at 0.",
"type": "integer"
},
"object": {
"const": "embedding",
"description": "Always embedding.",
"type": "string"
}
},
"required": [
"object",
"index",
"embedding"
],
"type": "object"
},
"type": "array"
},
"model": {
"description": "The model that embedded the input.",
"type": "string"
},
"object": {
"const": "list",
"description": "Always list.",
"type": "stri