Your trial endpoint

Send your first trial request.

Prepare trial credit and a key, send a request, then check the result and usage.

On this page

Prepare your trial

Store the key securely in your server environment as TIYUVTA_KEY. Never commit it.

Base URL: https://api.tiyuvta.ai/v1
Model ID: deepseek-ai/deepseek-v4.1-flash

Make a request

curl

curl https://api.tiyuvta.ai/v1/chat/completions \
  -H "Authorization: Bearer $TIYUVTA_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Say hello."}]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.tiyuvta.ai/v1", api_key=os.environ["TIYUVTA_KEY"])
response = client.chat.completions.create(
    model="deepseek-ai/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Say hello."}],
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.tiyuvta.ai/v1",
  apiKey: process.env.TIYUVTA_KEY,
});
const response = await client.chat.completions.create({
  model: "deepseek-ai/deepseek-v4.1-flash",
  messages: [{ role: "user", content: "Say hello." }],
});
console.log(response.choices[0].message.content);

These examples connect to the reference deployment. They do not qualify your workload or hardware. Use representative inputs and inspect the results.

Stream longer responses

Evaluate before you deploy

Compare answer quality, response time and usage on your workload. Your own deployment is a separate engagement.

Read trial documentation · Discuss your deployment