Skip to main content
POST
Create embedding

Authorizations

Authorization
string
header
required

Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.

Body

application/json
input
required

Text or token IDs to embed, supplied as one input or a list of inputs.

model
string | null

ID of the model to use.

user
string | null

Identifier for the end user, accepted for compatibility. Ignored by vLLM; other backends may use it.

truncate_prompt_tokens
integer | null

Maximum number of prompt tokens to keep. Use -1 for the model context limit. truncation_side selects which end is dropped; when unset, the backend uses its default.

Required range: x >= -1
truncation_side
enum<string> | null

Which side to truncate from when truncate_prompt_tokens is active. 'right' keeps the first N tokens. 'left' keeps the last N tokens.

Available options:
left,
right
request_id
string | null

The request_id related to this request. If the caller does not set it, a random uuid will be generated.

priority
integer
default:0

The priority of the request (lower means earlier handling; default: 0). Any priority other than 0 will raise an error if the served model does not use priority scheduling.

mm_processor_kwargs
Mm Processor Kwargs · object | null

Additional kwargs to pass to the HF processor.

cache_salt
string | null

If specified, the prefix cache will be salted with the provided string to prevent an attacker from guessing prompts in multi-user environments.

add_special_tokens
boolean
default:true

If true (the default), special tokens (e.g. BOS) will be added to the prompt.

encoding_format
enum<string>
default:float

Format of the returned embeddings. One of float, base64, bytes, or bytes_only. The two bytes formats return a binary response.

Available options:
float,
base64,
bytes,
bytes_only
embed_dtype
enum<string>
default:float32

What dtype to use for encoding. Defaults to float32 for base64 encoding to match the OpenAI python client behavior. Affects base64 and binary responses only.

Available options:
float32,
float16,
bfloat16,
fp8_e4m3,
fp8_e5m2
endianness
enum<string>
default:native

What endianness to use for encoding. Defaults to native to match the OpenAI python client behavior. Affects base64 and binary responses only.

Available options:
native,
big,
little
dimensions
integer | null

Number of dimensions in the returned embeddings. Supported only by models that allow shortened embeddings.

use_activation
boolean | null

Whether to use activation for the pooler outputs. null uses the pooler's default, which is true in most cases.

Response

Successful response.

id
string
required

Unique ID of the response.

created
integer
required

Unix timestamp, in seconds, of when the response was created.

data
EmbeddingResponseData · object[]
required

List of embeddings.

usage
UsageInfo · object
required
object
string
default:list

Object type. Always list.

model
string | null

ID of the model that generated the response.

Last modified on July 31, 2026