Generate chat completion

curl --request POST \
  --url https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "chat_history": [
    {
      "content": "<string>",
      "role": "user"
    }
  ],
  "prompt": "<string>",
  "temperature": 0.2,
  "stop_sequences": [
    "<string>"
  ],
  "max_tokens": 123,
  "top_p": 123,
  "top_k": 123,
  "frequency_penalty": 123,
  "presence_penalty": 123,
  "stream": false,
  "logprobs": true,
  "top_logprobs": 123,
  "chat_template": "<string>",
  "chat_template_kwargs": {}
}
'

import requests

url = "https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions"

payload = {
    "chat_history": [
        {
            "content": "<string>",
            "role": "user"
        }
    ],
    "prompt": "<string>",
    "temperature": 0.2,
    "stop_sequences": ["<string>"],
    "max_tokens": 123,
    "top_p": 123,
    "top_k": 123,
    "frequency_penalty": 123,
    "presence_penalty": 123,
    "stream": False,
    "logprobs": True,
    "top_logprobs": 123,
    "chat_template": "<string>",
    "chat_template_kwargs": {}
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    chat_history: [{content: '<string>', role: 'user'}],
    prompt: '<string>',
    temperature: 0.2,
    stop_sequences: ['<string>'],
    max_tokens: 123,
    top_p: 123,
    top_k: 123,
    frequency_penalty: 123,
    presence_penalty: 123,
    stream: false,
    logprobs: true,
    top_logprobs: 123,
    chat_template: '<string>',
    chat_template_kwargs: {}
  })
};

fetch('https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'chat_history' => [
        [
                'content' => '<string>',
                'role' => 'user'
        ]
    ],
    'prompt' => '<string>',
    'temperature' => 0.2,
    'stop_sequences' => [
        '<string>'
    ],
    'max_tokens' => 123,
    'top_p' => 123,
    'top_k' => 123,
    'frequency_penalty' => 123,
    'presence_penalty' => 123,
    'stream' => false,
    'logprobs' => true,
    'top_logprobs' => 123,
    'chat_template' => '<string>',
    'chat_template_kwargs' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions"

	payload := strings.NewReader("{\n  \"chat_history\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"user\"\n    }\n  ],\n  \"prompt\": \"<string>\",\n  \"temperature\": 0.2,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"frequency_penalty\": 123,\n  \"presence_penalty\": 123,\n  \"stream\": false,\n  \"logprobs\": true,\n  \"top_logprobs\": 123,\n  \"chat_template\": \"<string>\",\n  \"chat_template_kwargs\": {}\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions")
  .header("Content-Type", "application/json")
  .body("{\n  \"chat_history\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"user\"\n    }\n  ],\n  \"prompt\": \"<string>\",\n  \"temperature\": 0.2,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"frequency_penalty\": 123,\n  \"presence_penalty\": 123,\n  \"stream\": false,\n  \"logprobs\": true,\n  \"top_logprobs\": 123,\n  \"chat_template\": \"<string>\",\n  \"chat_template_kwargs\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"chat_history\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"user\"\n    }\n  ],\n  \"prompt\": \"<string>\",\n  \"temperature\": 0.2,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"frequency_penalty\": 123,\n  \"presence_penalty\": 123,\n  \"stream\": false,\n  \"logprobs\": true,\n  \"top_logprobs\": 123,\n  \"chat_template\": \"<string>\",\n  \"chat_template_kwargs\": {}\n}"

response = http.request(request)
puts response.read_body

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

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Models

Generate chat completion

Description

Interact with the LLM model using the specified model_deployment_id. You can include a list of messages as the conversation history. The conversation can feature multiple messages from the roles user, assistant, and system. If the chosen model does not support chat completion, the API will revert to simple completion, disregarding the provided history. The endpoint manages context length exceedance optimistically: it estimates the token count from the provided history and prompt, and if it exceeds the context or approaches 80% of it, the exact token count will be calculated, and the history will be trimmed to fit the context.

{
    "prompt": "Generate 5 more",
    "chat_history": [
        { "role": "system", "content": "You are a name generator. Do not generate anything else than names" },
        { "role": "user", "content": "Generate 5 names" },
        { "role": "assistant", "content": "1. Olivia Bennett\n2. Ethan Carter\n3. Sophia Ramirez\n4. Liam Thompson\n5. Ava Mitchell" }
    ],
}

POST

models

{model_deployment_id}

chat-completions

Generate chat completion

curl --request POST \
  --url https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "chat_history": [
    {
      "content": "<string>",
      "role": "user"
    }
  ],
  "prompt": "<string>",
  "temperature": 0.2,
  "stop_sequences": [
    "<string>"
  ],
  "max_tokens": 123,
  "top_p": 123,
  "top_k": 123,
  "frequency_penalty": 123,
  "presence_penalty": 123,
  "stream": false,
  "logprobs": true,
  "top_logprobs": 123,
  "chat_template": "<string>",
  "chat_template_kwargs": {}
}
'

import requests

url = "https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions"

payload = {
    "chat_history": [
        {
            "content": "<string>",
            "role": "user"
        }
    ],
    "prompt": "<string>",
    "temperature": 0.2,
    "stop_sequences": ["<string>"],
    "max_tokens": 123,
    "top_p": 123,
    "top_k": 123,
    "frequency_penalty": 123,
    "presence_penalty": 123,
    "stream": False,
    "logprobs": True,
    "top_logprobs": 123,
    "chat_template": "<string>",
    "chat_template_kwargs": {}
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    chat_history: [{content: '<string>', role: 'user'}],
    prompt: '<string>',
    temperature: 0.2,
    stop_sequences: ['<string>'],
    max_tokens: 123,
    top_p: 123,
    top_k: 123,
    frequency_penalty: 123,
    presence_penalty: 123,
    stream: false,
    logprobs: true,
    top_logprobs: 123,
    chat_template: '<string>',
    chat_template_kwargs: {}
  })
};

fetch('https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'chat_history' => [
        [
                'content' => '<string>',
                'role' => 'user'
        ]
    ],
    'prompt' => '<string>',
    'temperature' => 0.2,
    'stop_sequences' => [
        '<string>'
    ],
    'max_tokens' => 123,
    'top_p' => 123,
    'top_k' => 123,
    'frequency_penalty' => 123,
    'presence_penalty' => 123,
    'stream' => false,
    'logprobs' => true,
    'top_logprobs' => 123,
    'chat_template' => '<string>',
    'chat_template_kwargs' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions"

	payload := strings.NewReader("{\n  \"chat_history\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"user\"\n    }\n  ],\n  \"prompt\": \"<string>\",\n  \"temperature\": 0.2,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"frequency_penalty\": 123,\n  \"presence_penalty\": 123,\n  \"stream\": false,\n  \"logprobs\": true,\n  \"top_logprobs\": 123,\n  \"chat_template\": \"<string>\",\n  \"chat_template_kwargs\": {}\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions")
  .header("Content-Type", "application/json")
  .body("{\n  \"chat_history\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"user\"\n    }\n  ],\n  \"prompt\": \"<string>\",\n  \"temperature\": 0.2,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"frequency_penalty\": 123,\n  \"presence_penalty\": 123,\n  \"stream\": false,\n  \"logprobs\": true,\n  \"top_logprobs\": 123,\n  \"chat_template\": \"<string>\",\n  \"chat_template_kwargs\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v4/models/{model_deployment_id}/chat-completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"chat_history\": [\n    {\n      \"content\": \"<string>\",\n      \"role\": \"user\"\n    }\n  ],\n  \"prompt\": \"<string>\",\n  \"temperature\": 0.2,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"max_tokens\": 123,\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"frequency_penalty\": 123,\n  \"presence_penalty\": 123,\n  \"stream\": false,\n  \"logprobs\": true,\n  \"top_logprobs\": 123,\n  \"chat_template\": \"<string>\",\n  \"chat_template_kwargs\": {}\n}"

response = http.request(request)
puts response.read_body

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

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Path Parameters

model_deployment_id

string

required

Body

application/json

Represents a chat completion request.

Attributes: chat_history (List[Message]): Chat history

chat_history

(User Message · object | Assistant Message · object | System Message · object)[]

required

Chat history entries with roles and messages. If there's no history, pass an empty list.

User Message
Assistant Message
System Message

Show child attributes

prompt

string

required

New user prompt. This will be sent to the model with a user role.

model_request_parameters

ParameterBindings · object

Show child attributes

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.

Maximum array length: 4

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 family	Model API default	EGP applied default
OpenAI Completions	`16`	`context window - prompt size`
OpenAI Chat Completions	`context window - prompt size`	`context window - prompt size`
LLM Engine	`max_new_tokens` parameter is required	`100`
Anthropic Claude 2	`max_tokens_to_sample` parameter is required	`10000`

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

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

Successful Response

completions

tuple[]

required

Show child attributes

finish_reason

string

prompt_tokens

integer

default:0

response_tokens

integer

default:0

choices

Choice · object[]

Show child attributes

Knowledge Bases

Chunks

Agents

Completions

Chat Completions

Models

Users

Accounts

Organizations

Question Sets

Evaluations

Evaluation Configs

Evaluation Datasets

Studio Projects

Application Specs

Questions

Knowledge Base Data Sources

Model Templates V3 (Beta)

Model server

API Reference

Fine Tuning Jobs V3 (Beta)

Training Datasets V3 (Beta)

package deployments

Beta

Applications

ChatThreads

Interactions

MonitoringDashboard

Chat Themes

Sessions

account groups

Generate chat completion

Description

Path Parameters

Body

Response