Chat Completions

POST

/project/p-{Project_Id}/endpoint/is-{Endpoint_Id}/v1/chat/completions

curl --request POST \
  --url 'https://api.e2enetworks.com/myaccount/api/v1/gpu/project/p-{Project_Id}/endpoint/is-{Endpoint_Id}/v1/chat/completions?project_id=<PROJECT_ID>&apikey=<API_KEY>' \
  --header 'Authorization: Bearer <API_TOKEN>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "your-model-name",
  "messages": [
    {
      "role": "user",
      "content": "Hello!!"
    }
  ],
  "max_tokens": 512,
  "temperature": 0.7,
  "top_p": 1,
  "top_k": 50,
  "frequency_penalty": 0,
  "stream": false
}'

import requests

response = requests.post(
    "https://api.e2enetworks.com/myaccount/api/v1/gpu/project/p-{Project_Id}/endpoint/is-{Endpoint_Id}/v1/chat/completions",
    params={"project_id": "<PROJECT_ID>", "apikey": "<API_KEY>"},
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "model": "your-model-name",
        "messages": [
            {
                "role": "user",
                "content": "Hello!!",
            },
        ],
        "max_tokens": 512,
        "temperature": 0.7,
        "top_p": 1,
        "top_k": 50,
        "frequency_penalty": 0,
        "stream": False,
    },
)
print(response.json())

const url = new URL("https://api.e2enetworks.com/myaccount/api/v1/gpu/project/p-{Project_Id}/endpoint/is-{Endpoint_Id}/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({
    "model": "your-model-name",
    "messages": [
      {
        "role": "user",
        "content": "Hello!!"
      }
    ],
    "max_tokens": 512,
    "temperature": 0.7,
    "top_p": 1,
    "top_k": 50,
    "frequency_penalty": 0,
    "stream": false
  }),
});
console.log(await response.json());

Generate chat completions using a deployed model endpoint. Supports any model deployed via TIR Inference Service, following the OpenAI-compatible chat completions API format.

Parameters

Path Parameters

Project_Id

required

string

Path parameter Project_Id.

Endpoint_Id

required

string

Query Parameters

project_id

required

integer

Project ID

Request Body

application/json

object

model

required

The model identifier to use for completion.

string

Example

your-model-name

messages

required

A list of messages comprising the conversation so far.

Array<object>

object

role

string

Allowed values: user system assistant

Example

user

content

string

Example

Hello!!

max_tokens

Maximum number of tokens to generate in the response.

integer

Example

temperature

Controls randomness. Lower values make output more deterministic, higher values more creative.

number

Example

0.7

top_p

Nucleus sampling probability mass. Only tokens with cumulative probability up to top_p are considered.

number

Example

top_k

Limits the number of highest-probability tokens considered at each step.

integer

Example

frequency_penalty

Penalizes tokens based on how frequently they have appeared in the text so far.

number

Example

stream

If true, responses are streamed as server-sent events.

boolean

Example

false

Responses

200

Successful chat completion response.

application/json

object

Unique identifier for the completion.

string

object

Object type, always chat.completion.

string

created

Unix timestamp of when the completion was created.

integer

model

The model used for the completion.

string

choices

List of generated completion choices.

Array<object>

object

index

integer

message

object

role

string

content

string

refusal

string

nullable

tool_calls

Array<object>

object

reasoning

string

nullable

logprobs

string

nullable

finish_reason

string

stop_reason

string

nullable

token_ids

string

nullable

service_tier

string

nullable

system_fingerprint

string

nullable

usage

object

prompt_tokens

integer

completion_tokens

integer

total_tokens

integer

prompt_tokens_details

string

nullable

prompt_logprobs

string

nullable

prompt_token_ids

string

nullable

kv_transfer_params

string

nullable

Example

{
  "id": "chatcmpl-ab36a36c-2315-472f-9e58-0f68f19b8bf8",
  "object": "chat.completion",
  "created": 1776750085,
  "model": "meta-llama/Llama-3.2-1B-Instruct",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "In Nature's embrace, I find my peace,\nA world of wonder, a world to cease,\nFrom mountains high to valleys low,\nA tapestry of life, in all its glow.",
        "refusal": null,
        "tool_calls": [],
        "reasoning": null
      },
      "logprobs": null,
      "finish_reason": "stop",
      "stop_reason": null,
      "token_ids": null
    }
  ],
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "prompt_tokens": 40,
    "completion_tokens": 274,
    "total_tokens": 314,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "kv_transfer_params": null
}