GET

/v1/schemas/cohere/embeddings/v2/embed

Accept:

kind inputactivity embeddingshash 1ec6dada…extracted Sep 30, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `814093aac6748d91ca9e6886970b11b34bf2edcf03c4eafac622f17c18e5c851` { "fetchedAt": 1790746305, "extractorVersion": "1", "verifiedAt": null }

Request body

10 properties · 2 required · 8 $defs

property	type	description	constraints
model*	string	ID of one of the available [Embedding models](https://docs.cohere.com/docs/cohere-embed).
input_type*	enum	Specifies the type of input passed to the model. Required for embedding models v3 and higher.	search_document \| search_query \| classification \| clustering \| image
texts	string[]	An array of strings for the model to embed. Maximum number of texts per call is `96`.	items ≥ 1 · items ≤ 96
images	string[]	An array of image data URIs for the model to embed.	items ≥ 1
inputs	EmbedInput[]	An array of inputs for the model to embed. Maximum number of inputs per call is `96`. An input can contain a mix of text and image components.
max_tokens	integer	The maximum number of tokens to embed per input. If the input text is longer than this, it will be truncated according to the `truncate` parameter.
output_dimension	integer	The number of dimensions of the output embedding. This is only available for `embed-v4` and newer models. For supported dimensions, please refer to the [Embed models](https://docs.cohere.com/docs/cohere-embed) page.
embedding_types	EmbeddingType[]	Specifies the types of embeddings you want to get back. Can be one or more of the following types.	default: ["float"]
truncate	enum	One of `NONE\|START\|END` to specify how the API will handle inputs longer than the maximum token length.	NONE \| START \| END · default: "END"
priority	integer	Controls how early the request is handled. Lower numbers indicate higher priority (default: 0, the highest). When the system is under load, higher-priority requests are processed first and are the least likely to be dropped.	0 ≤ n ≤ 999 · default: 0

Types

8 $defs

EmbedContentobject | object

EmbedContentTypeenum

text | image_url

EmbeddingTypeenum

EmbedImageobject

Image content of the input. Supported with Embed v3.0 and newer models.

type	enum		text \| image_url
image_url	EmbedImageUrl	Base64 url of image.

EmbedImageUrlobject

Base64 url of image.

url*

string

EmbedInputobject

content*

EmbedContent[]

An array of objects containing the input data for the model to embed.

EmbedInputTypeenum

Specifies the type of input passed to the model. Required for embedding models v3 and higher.

search_document | search_query | classification | clustering | image

EmbedTextobject

Text content of the input.

type	enum		text \| image_url
text	string

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"cohere","endpointId":"v2/embed","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}