Create Embedding

Create text embeddings. Returns vector representations of the input text.

Authentication

AuthorizationBearer

Your production key sent as a bearer token.

Request

This endpoint expects an object.

modelstringRequired

Model ID in format ‘provider/model-name’

inputstring or list of stringsRequired

Text to embed

encoding_formatstring or nullOptional

Encoding format for embeddings

dimensionsinteger or nullOptional

Number of dimensions for the output embeddings. Supported by OpenAI text-embedding-3 and later models and by Google gemini embedding models.

task_typestring or nullOptional

Google-only: the embedding task type (e.g. RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING). Ignored for non-Google models.

userstring or nullOptional

End-user identifier

Response

Successful Response

datalist of objects

modelstring

usageobject

Token usage for embeddings.

object"list"OptionalDefaults to list

Errors

422

Unprocessable Entity Error

$	curl -X POST https://api-gateway.merge.dev/v1/embeddings \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "openai/text-embedding-3-small",
>	"input": "The quick brown fox jumps over the lazy dog."
>	}'

1	{
2	"data": [
3	{
4	"embedding": [
5	0.0023064255,
6	-0.009327292,
7	0.015797347,
8	-0.0034413044,
9	0.008719321
10	],
11	"index": 0,
12	"object": "embedding"
13	}
14	],
15	"model": "openai/text-embedding-3-small",
16	"usage": {
17	"prompt_tokens": 10,
18	"total_tokens": 10,
19	"cost": 2e-7
20	},
21	"object": "list"
22	}