Tradeics AI

Call the LLM

Updated on July 13, 2026

Call Tradeics models through the OpenAI-compatible proxy at https://llm.tradeics.example.

The LLM API Reference right panel shows live HTTP request/response samples per endpoint. This guide adds copy-paste clients in multiple languages.

Base URL

Use	URL
Proxy root	`https://llm.tradeics.example`
OpenAI SDK `base_url`	`https://llm.tradeics.example/v1`
Chat	`POST /v1/chat/completions`
Models	`GET /v1/models`
Embeddings	`POST /v1/embeddings`

Authenticate

export TRADEICS_LLM_API_KEY="sk-..."

Authorization: Bearer $TRADEICS_LLM_API_KEY

List models

curl https://llm.tradeics.example/v1/models \
  -H "Authorization: Bearer $TRADEICS_LLM_API_KEY"

Chat completion — multi-language

Replace <model_id> with an id from /v1/models.

cURL

curl https://llm.tradeics.example/v1/chat/completions \
  -H "Authorization: Bearer $TRADEICS_LLM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model_id>",
    "messages": [
      {"role": "system", "content": "You help procurement teams evaluate B2B suppliers."},
      {"role": "user", "content": "Summarize this RFQ in three bullets."}
    ],
    "temperature": 0.2
  }'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["TRADEICS_LLM_API_KEY"],
    base_url="https://llm.tradeics.example/v1",
)

response = client.chat.completions.create(
    model="<model_id>",
    messages=[
        {"role": "system", "content": "You help procurement teams evaluate B2B suppliers."},
        {"role": "user", "content": "Draft three clarifying questions for this RFQ."},
    ],
)

print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TRADEICS_LLM_API_KEY,
  baseURL: "https://llm.tradeics.example/v1",
});

const response = await client.chat.completions.create({
  model: "<model_id>",
  messages: [
    { role: "system", content: "You help procurement teams evaluate B2B suppliers." },
    { role: "user", content: "Turn this supplier email into a structured quote summary." },
  ],
});

console.log(response.choices[0].message.content);

Go

package main

import (
  "bytes"
  "encoding/json"
  "fmt"
  "net/http"
  "os"
)

func main() {
  body := map[string]any{
    "model": "<model_id>",
    "messages": []map[string]string{
      {"role": "system", "content": "You help procurement teams evaluate B2B suppliers."},
      {"role": "user", "content": "Score these three suppliers briefly."},
    },
  }
  b, _ := json.Marshal(body)
  req, _ := http.NewRequest("POST", "https://llm.tradeics.example/v1/chat/completions", bytes.NewReader(b))
  req.Header.Set("Authorization", "Bearer "+os.Getenv("TRADEICS_LLM_API_KEY"))
  req.Header.Set("Content-Type", "application/json")
  res, err := http.DefaultClient.Do(req)
  if err != nil { panic(err) }
  defer res.Body.Close()
  fmt.Println(res.Status)
}

PHP

<?php
$payload = [
  "model" => "<model_id>",
  "messages" => [
    ["role" => "system", "content" => "You help procurement teams evaluate B2B suppliers."],
    ["role" => "user", "content" => "Summarize this RFQ in three bullets."],
  ],
];

$ch = curl_init("https://llm.tradeics.example/v1/chat/completions");
curl_setopt_array($ch, [
  CURLOPT_POST => true,
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer " . getenv("TRADEICS_LLM_API_KEY"),
    "Content-Type: application/json",
  ],
  CURLOPT_POSTFIELDS => json_encode($payload),
  CURLOPT_RETURNTRANSFER => true,
]);
echo curl_exec($ch);

Java

var client = HttpClient.newHttpClient();
var json = """
  {
    "model": "<model_id>",
    "messages": [
      {"role": "system", "content": "You help procurement teams evaluate B2B suppliers."},
      {"role": "user", "content": "Summarize this RFQ in three bullets."}
    ]
  }
  """;
var request = HttpRequest.newBuilder()
  .uri(URI.create("https://llm.tradeics.example/v1/chat/completions"))
  .header("Authorization", "Bearer " + System.getenv("TRADEICS_LLM_API_KEY"))
  .header("Content-Type", "application/json")
  .POST(HttpRequest.BodyPublishers.ofString(json))
  .build();
var response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

Ruby

require "net/http"
require "json"
require "uri"

uri = URI("https://llm.tradeics.example/v1/chat/completions")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{ENV["TRADEICS_LLM_API_KEY"]}"
req["Content-Type"] = "application/json"
req.body = {
  model: "<model_id>",
  messages: [
    { role: "system", content: "You help procurement teams evaluate B2B suppliers." },
    { role: "user", content: "Summarize this RFQ in three bullets." }
  ]
}.to_json

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
puts res.body

Embeddings

curl https://llm.tradeics.example/v1/embeddings \
  -H "Authorization: Bearer $TRADEICS_LLM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<embedding_model_id>",
    "input": ["M8 hex bolt stainless", "hydraulic pump 5HP"]
  }'

Production checklist

Keep keys on the server only.
Log model + latency — not secrets inside prompts.
Treat model output as assistive before awarding POs or releasing payments.
Use REST API V2 for masters and transactions; this LLM API for inference.
Prefer MCP when an agent should operate on workspace data (not for high-volume batch inference).