Embeddings API Reference

deployment-id

template

true

string

Model ID of the model to use for this request. The available models are text-embedding-3-large, embed-v-4-0, and qwen3-embedding.

model

true

string

Model ID of the model to use for this request. The available models are text-embedding-3-large, embed-v-4-0, and qwen3-embedding.

input

true

string, array

Text to embed, encoded as a string. To embed multiple inputs in a single request, pass an array of strings. The maximum length of input text for our latest embedding models is 8192 tokens. You should verify that your inputs don't exceed this limit before making a request. If sending an array of inputs in a single embedding request, the maximum array size is 2048.
Note: Unless you are embedding code, it is suggested to replace newlines (\n) in your input with a single space, as inferior results are observed when newlines are present.

texts

false

list of strings

An array of strings for the model to embed. Maximum number of texts per call is 96.

Note: This parameter is available only with the Cohere Embed 4 model.

dimensions

false

integer

The number of dimensions the resulting output embeddings should have.
Note: This parameter is only supported in text-embedding-3-large and later models.

user

false

string

A unique identifier represents your end-user.

input_type

false

string

The input type used for embedding searches.

ts

false

string

Timestamp of the request. For example, 2024-03-18T05:40:18.264Z.

encoding_format

false

string

The format to return the embeddings in. Values can be either float or base64. The default value is float.

embedding_types

false

list of enums

Specifies the types of embeddings you want to get back. Can be one or more of the following types.

• "float": Use this when you want to get back the default float embeddings.

• "int8": Use this when you want to get back signed int8 embeddings.

• "uint8": Use this when you want to get back unsigned int8 embeddings.

• "binary": Use this when you want to get back signed binary embeddings.

• "ubinary": Use this when you want to get back unsigned binary embeddings.

Allowed values:float, int8, uint8, binary, ubinary

Note: This parameter is available only with the Cohere Embed 4 model.

output_dimension

Optional

integer

The number of dimensions of the output embedding. This is only available for embed-v4 and newer models. Possible values are 256, 512, 1024, and 1536. The default is 1536.

Note: This parameter is available only with the Cohere Embed 4 models.