Developer Quickstart | Kryyt Developers

Create a project

Sign in to Kryyt.
Open API & developers in the account menu and create an API project.
Create a key, copy it when shown, and keep it on your server.
Add purchased credits before making a request.

Set your environment

Shell

export KRYYT_API_KEY="kryyt_your_project_key"

PowerShell

$env:KRYYT_API_KEY = "kryyt_your_project_key"

Replace the placeholder with the key issued by Kryyt. Python examples require the openai package; Node.js examples require the openai package in a server-side project.

Make a request

cURL

curl https://api.kryyt.com/v1/chat/completions \
  -H "Authorization: Bearer $KRYYT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4.1-flash","messages":[{"role":"user","content":"Explain caching in two sentences."}],"max_tokens":512}'

Python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.kryyt.com/v1",
    api_key=os.environ["KRYYT_API_KEY"],
    timeout=600,
    max_retries=0,
)

response = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Explain caching in two sentences."}],
    max_tokens=512,
)
print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.kryyt.com/v1",
  apiKey: process.env.KRYYT_API_KEY,
  timeout: 600_000,
  maxRetries: 0,
});

const response = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [{role: "user", content: "Explain caching in two sentences."}],
  max_tokens: 512,
});
console.log(response.choices[0].message.content);

Discover available models

The current launch model is deepseek-v4.1-flash. Discover active model IDs with an authenticated request rather than assuming catalog or roadmap entries are available.

List models

curl https://api.kryyt.com/v1/models -H "Authorization: Bearer $KRYYT_API_KEY"

Compatibility at a glance

Endpoint	Status
`GET /v1/models`	List active models
`GET /v1/models/{id}`	Retrieve a chat model
`POST /v1/chat/completions`	Text, supported image input, streaming, and function declarations
`POST /v1/completions`	Completion requests for a supported model
Responses, Assistants, embeddings, audio, image generation, and OpenAI file uploads	Not implemented by this gateway