Llama 3.1 8B Instruct

POST

/project/p-{Project_Id}/genai/llama3_1_8b_instruct/v1/chat/completions

curl --request POST \
  --url 'https://api.e2enetworks.com/myaccount/api/v1/gpu/project/p-{Project_Id}/genai/llama3_1_8b_instruct/v1/chat/completions?project_id=<PROJECT_ID>&apikey=<API_KEY>' \
  --header 'Authorization: Bearer <API_TOKEN>' \
  --header 'Content-Type: application/json' \
  --data '{
  "temperature": 0.5,
  "max_tokens": 1024,
  "top_p": 1,
  "frequency_penalty": 0,
  "presence_penalty": 1,
  "stream": false,
  "model": "llama3_1_8b_instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

import requests

response = requests.post(
    "https://api.e2enetworks.com/myaccount/api/v1/gpu/project/p-{Project_Id}/genai/llama3_1_8b_instruct/v1/chat/completions",
    params={"project_id": "<PROJECT_ID>", "apikey": "<API_KEY>"},
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "temperature": 0.5,
        "max_tokens": 1024,
        "top_p": 1,
        "frequency_penalty": 0,
        "presence_penalty": 1,
        "stream": False,
        "model": "llama3_1_8b_instruct",
        "messages": [
            {
                "role": "user",
                "content": "Hello",
            },
        ],
    },
)
print(response.json())

const url = new URL("https://api.e2enetworks.com/myaccount/api/v1/gpu/project/p-{Project_Id}/genai/llama3_1_8b_instruct/v1/chat/completions");
url.search = new URLSearchParams({ project_id: "<PROJECT_ID>", apikey: "<API_KEY>" });

const response = await fetch(url, {
  method: "POST",
  headers: { "Authorization": "Bearer <API_TOKEN>", "Content-Type": "application/json" },
  body: JSON.stringify({
    "temperature": 0.5,
    "max_tokens": 1024,
    "top_p": 1,
    "frequency_penalty": 0,
    "presence_penalty": 1,
    "stream": false,
    "model": "llama3_1_8b_instruct",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }),
});
console.log(await response.json());

Llama 3.1 represents Meta’s most advanced language model to date. It integrates state-of-the-art techniques in natural language processing to deliver unparalleled performance in various tasks.

Parameters

Path Parameters

Project_Id

required

string

Path parameter Project_Id.

Query Parameters

project_id

required

integer

Project ID

Request Body

application/json

object

temperature

number

default: 0.5

max_tokens

integer

default: 1024

top_p

number

default: 1

frequency_penalty

number

presence_penalty

number

default: 1

stream

boolean

model

string

Example

llama3_1_8b_instruct

messages

Array<object>

object

role

string

Example

user

content

string

Example

Hello

Responses

default

Successful response (Non-streaming)

application/json

object

string

object

string

created

integer

model

string

choices

Array<object>

object

index

integer

message

object

role

string

content

string

tool_calls

Array<string>

logprobs

string

nullable

finish_reason

string

stop_reason

string

nullable

usage

object

prompt_tokens

integer

completion_tokens

integer

total_tokens

integer

Example

{
  "id": "chat-a8fa533f74b346688f780c3b2e14638f",
  "object": "chat.completion",
  "created": 1738753122,
  "model": "llama3_1_8b_instruct",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "It looks like we're saying hello twice. How's your day going so far?",
        "tool_calls": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 56,
    "completion_tokens": 18,
    "total_tokens": 74
  }
}