POST
/
v4
/
models
/
{model_deployment_id}
/
completions
import SGPClient from 'sgp';

const client = new SGPClient({
  apiKey: process.env['SGP_API_KEY'], // This is the default and can be omitted
});

async function main() {
  const completionResponse = await client.models.completions.create('model_deployment_id', {
    prompt: 'prompt',
  });

  console.log(completionResponse.completions);
}

main();
{
  "finish_reason": "<string>",
  "prompt_tokens": 0,
  "response_tokens": 0,
  "completions": [
    [
      "<any>"
    ]
  ],
  "choices": [
    {
      "index": 123,
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "bytes": [
              123
            ],
            "logprob": 123,
            "top_logprobs": [
              {
                "token": "<string>",
                "bytes": [
                  123
                ],
                "logprob": 123
              }
            ]
          }
        ]
      }
    }
  ]
}

Authorizations

​
x-api-key
string
header
required

Headers

​
x-selected-account-id
string

Path Parameters

​
model_deployment_id
string
required

Body

application/json
​
prompt
string
required
​
model_request_parameters
object
​
temperature
number
default:0.2

What sampling temperature to use, between [0, 2]. Higher values like 1.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. Setting temperature=0.0 will enable fully deterministic (greedy) sampling.NOTE: The temperature parameter range for some model is limited to [0, 1] if the given value is above the available range, it defaults to the max value. Temperature is ignored for OpenAI reasoning models.

Required range: 0 <= x <= 2
​
stop_sequences
string[]

List of up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

​
max_tokens
integer

The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. If not, specified, max_tokens will be determined based on the model used:

Model API familyModel API defaultEGP applied default
OpenAI Completions16context window - prompt size
OpenAI Chat Completionscontext window - prompt sizecontext window - prompt size
LLM Enginemax_new_tokens parameter is required100
Anthropic Claude 2max_tokens_to_sample parameter is required10000
​
top_p
number

The cumulative probability cutoff for token selection. Lower values mean sampling from a smaller, more top-weighted nucleus. Available for models provided by Google, LLM Engine, and OpenAI.

​
top_k
number

Sample from the k most likely next tokens at each step. Lower k focuses on higher probability tokens. Available for models provided by Google and LLM Engine.

​
frequency_penalty
number

Penalize tokens based on how much they have already appeared in the text. Positive values encourage the model to generate new tokens and negative values encourage the model to repeat tokens. Available for models provided by LLM Engine and OpenAI.

​
presence_penalty
number

Penalize tokens based on if they have already appeared in the text. Positive values encourage the model to generate new tokens and negative values encourage the model to repeat tokens. Available for models provided by LLM Engine and OpenAI.

​
stream
boolean
default:false

Flag indicating whether to stream the completion response

​
logprobs
boolean

Whether to return logprobs. Currently only supported for llmengine chat models.

​
top_logprobs
integer

Number of top logprobs to return. Currently only supported for llmengine chat models.

​
chat_template
string

The chat template to use for the completion. Currently only supported for llmengine chat models.

​
chat_template_kwargs
object

Additional keyword arguments for the chat template. Currently only supported for llmengine chat models.

​
reasoning_effort
enum<string>

The reasoning effort to use for the completion. Currently only supported for openai models.

Available options:
low,
medium,
high

Response

200
application/json
Successful Response
​
completions
array
required
​
finish_reason
string
​
prompt_tokens
integer
default:0
​
response_tokens
integer
default:0
​
choices
object[]