GET

/v1/schemas/gemini/embeddings/v1beta/models/{modelsId}:batchEmbedContents?kind=output

Accept:

kind outputactivity embeddingshash 313e8aec…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `f697c69526f2d0f93e6e022d34a6a98146776f0f982cc56727132c048329221c` { "fetchedAt": 1783328683, "extractorVersion": "1", "verifiedAt": null }

Response body

2 properties · 0 required · 3 $defs

property	type	description	constraints
embeddings	ContentEmbedding[]	Output only. The embeddings for each request, in the same order as provided in the batch request.
usageMetadata	EmbeddingUsageMetadata	Metadata on the usage of the embedding request.

Types

3 $defs

ContentEmbeddingobject

A list of floats representing an embedding.

values	number[]	The embedding values. This is for 3P users only and will not be populated for 1P calls.
shape	integer[]	This field stores the soft tokens tensor frame shape (e.g. [1, 1, 256, 2048]).

EmbeddingUsageMetadataobject

Metadata on the usage of the embedding request.

promptTokenCount	integer	Output only. Number of tokens in the prompt.	format: int32
promptTokenDetails	ModalityTokenCount[]	Output only. List of modalities that were processed in the request input.

ModalityTokenCountobject

Represents token counting info for a single modality.

tokenCount	integer	Number of tokens.	format: int32
modality	enum	The modality associated with this token count.	MODALITY_UNSPECIFIED \| TEXT \| IMAGE \| VIDEO \| AUDIO \| DOCUMENT

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"gemini","endpointId":"v1beta/models/{modelsId}:batchEmbedContents","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}