Quickstart

Your first Devotel AI request, in about two minutes.

Get an API key

The full key is shown once, at creation. Only its first 8 characters are stored for display — the rest is kept as a SHA-256 hash, so nobody, including us, can recover it. Copy it before closing the dialog.

Export it


export DEVOTEL_API_KEY="dvt-your-key-here"

Send a request

curl


curl https://api.devotel.com/v1/chat/completions \
  -H "Authorization: Bearer $DEVOTEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [
      {"role": "user", "content": "Say hello in exactly five words."}
    ]
  }'

Python


pip install openai


import os
from openai import OpenAI
 
client = OpenAI(
    api_key=os.environ["DEVOTEL_API_KEY"],
    base_url="https://api.devotel.com/v1",
)
 
response = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Say hello in exactly five words."}],
)
 
print(response.choices[0].message.content)

JavaScript


npm install openai


import OpenAI from 'openai'
 
const client = new OpenAI({
  apiKey: process.env.DEVOTEL_API_KEY,
  baseURL: 'https://api.devotel.com/v1',
})
 
const response = await client.chat.completions.create({
  model: 'kimi-k3',
  messages: [{ role: 'user', content: 'Say hello in exactly five words.' }],
})
 
console.log(response.choices[0].message.content)

What comes back


{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "kimi-k3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello there, how are you?",
        "reasoning_content": "The user asked me to say hello in exactly five words. Let me count..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 95,
    "completion_tokens": 158,
    "total_tokens": 253,
    "completion_tokens_details": { "reasoning_tokens": 141 }
  }
}

Two things worth noticing in that response:

reasoning_content holds the model’s thinking. It is not part of the answer — render content and keep the reasoning collapsed or drop it.
completion_tokens is 158 for a 25-character answer, because 141 of those tokens were reasoning. Reasoning is billed at the output rate. See Models.

Next steps

Streaming — token-by-token output
Tool Calling & Agents — let the model call your functions
Chat Completions — every supported parameter