Create text embeddings

POST

/v1/embeddings

Generate Gemini embeddings. Use dimensions=768 for the platform document index; do not mix vectors from different models.

Request

Body Params application/jsonRequired

Examples

Responses

🟢200

application/json

Embedding vectors

Headers

Bodyapplication/json

🟠400BadRequest

🟠401Unauthorized

🔴502ProviderError

🔴503Unavailable

Request Example

Shell

JavaScript

Java

Swift

cURL

Single stringBatch of strings

curl --location '/v1/embeddings' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gemini-embedding-001",
    "input": "The quick brown fox jumps over the lazy dog.",
    "provider": "gemini"
}'

Response Example

200 - Example 1

{
    "object": "list",
    "data": [
        {
            "object": "embedding",
            "index": 0,
            "embedding": [
                0
            ]
        }
    ],
    "model": "string",
    "usage": {
        "prompt_tokens": 0,
        "total_tokens": 0
    }
}

Modified at 2026-10-20 19:28:20

Create a chat completion

Transcribe audio with AWS Transcribe