Endpoint Specification

Endpoint

Available endpoint

/{dedicate}/v1/chat/completions

Method

Post

Autherization : "Bearer {your-apikey}"

Request parameter

ParameterDescriptionRequired

messages

Messages must be in the same format as the OpenAI API format

[

{

"role" : "system", "user", "assistant"

},

{

"content" : "text"

}

]

Yes

model

The model should be from a Huggingface model repository.

i.e. SeaLLMs/SeaLLMs-v3-1.5B-Chat

Yes

stream

Boolean, By default is False

No

max_tokens

Int, By default is 1024

No

temperature

Float, By default is 0.7

No

repetition_penalty

Float, By default is 1.0

No

end_id

Int, By default uses eos_token_id from config.json of the model repository.

No

top_p

Float, By default is 0.7

No

top_k

Int, By default is 40

No

stop

Array, By default uses eos_token from config.json of the model repository.

No

random_sed

Int, By default is 2

No

/{dedicate}/v1/completions

Method

Post

Header

Autherization : "Bearer {your-apikey}"

Request parameter

ParameterDescriptionRequired

prompt

A prompt is the raw text and is not modified by applying a chat template.

A prompt must be used when you need to use a base model or a coding model. When using a coding model via the Continue.dev extension, the prompt will automatically be passed to the endpoint.

Yes

model

The model should be from a Huggingface model repository. i.e. SeaLLMs/SeaLLMs-v3-1.5B-Chat

Yes

stream

Boolean, By default is False

No

max_tokens

Int, By default is 1024

No

temperature

Float, By default is 0.7

No

repetition_penalty

Float, By default is 1.0

No

end_id

Int, By default uses eos_token_id from config.json of the model repository.

No

top_p

Float, By default is 0.7

No

top_k

Int, By default is 40

No

stop

Array, By default uses eos_token from config.json of the model repository.

No

random_sed

Int, By default is 2

No

Last updated