Chat Completion

POSThttps://zylai-a779.zyllion.network/v1/chat/completions

info

Feel free to use the Zyllion2025 as a test Bearer Token

Generate a chat completion response from the AI model.

  • req: Chat completion request containing messages and model specifications

  • user: Authenticated user information (through HTTP Bearer header)

  • Returns: Full chat response with model output, usage statistics, and cryptographic signature

Request Requirements​

  • Must include non-empty list of messages

  • Must specify a model

  • Supports multiple message formats (system, user, assistant)

Response Components​

  • Model-generated text completion

  • Token usage metrics

  • Cryptographically signed response for verification

Processing Steps​

  1. Validate input request parameters

  2. Prepare messages for model processing

  3. Generate AI model response

  4. Track and update token usage

  5. Cryptographically sign the response

Potential HTTP Errors​

  • 400 Bad Request:

    • Missing messages list

    • No model specified

  • 500 Internal Server Error:

    • Model fails to generate a response

Request​

  • application/json

Responses​

  • 200

  • 422

Successful Response

  • application/json

  • Schema

  • curl

  • dart

  • go

  • http

  • java

  • javascript

  • kotlin

  • c

  • nodejs

  • objective-c

  • ocaml

  • php

  • powershell

  • python

  • r

  • ruby

  • rust

  • shell

  • swift

  • HTTPCLIENT

  • RESTSHARP

var client = new HttpClient();
var request = new HttpRequestMessage(HttpMethod.Post, "https://zylai-a779.zyllion.network/v1/chat/completions");
request.Headers.Add("Accept", "application/json");
request.Headers.Add("Authorization", "Bearer <TOKEN>");
var content = new StringContent("{\n  \"model\": \"meta-llama/Llama-3.1-8B-Instruct\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"What is your name?\"\n    }\n  ],\n  \"temperature\": 0.2,\n  \"top_p\": 0.95,\n  \"max_tokens\": 2048,\n  \"stream\": false,\n  \"zylrag\": {}\n}", null, "application/json");
request.Content = content;
var response = await client.SendAsync(request);
response.EnsureSuccessStatusCode();
Console.WriteLine(await response.Content.ReadAsStringAsync());

RequestCollapse all

Send API RequestResponseClear

Click the Send API Request button above and see the response here!

PreviousOverviewNextAttestation

Last updated