Gonka24 developer documentation

Start building with Gonka24.

Connect an OpenAI-compatible client, choose a live model ID, and make your first request in a few minutes.

Choose your path

SDK or HTTP API

Connect an existing application with cURL, Python, or the OpenAI TypeScript SDK.

Coding agent

Configure Cursor, Cline, Continue, or Aider around the same endpoint.

Claude Code

Connect Claude Code through the Anthropic-compatible Messages API adapter.

Production application

Keep keys server-side, rotate them when exposed, and plan for retries.

Connection details

Gonka24 accepts OpenAI-compatible Chat Completions requests. Your client needs a custom base URL, a dashboard API key, and a model ID returned by the API.

Base URL: https://api.gonka24.com/v1
Authentication: Bearer sk-...
Model: GET /v1/models

Use a live model ID.

The catalog changes. Call GET /v1/models with your API key and copy an id from the response instead of relying on a model name in a guide.

bash

curl https://api.gonka24.com/v1/models \
  -H "Authorization: Bearer $GONKA24_API_KEY"

Make your first request

Create an API key in the dashboard, export it only in your terminal or server environment, replace <model-id> with an ID from /v1/models, then run:

bash

export GONKA24_API_KEY="sk-..."

curl https://api.gonka24.com/v1/chat/completions \
  -H "Authorization: Bearer $GONKA24_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model-id-from-/v1/models>",
    "messages": [{ "role": "user", "content": "Hello from Gonka24" }]
  }'

Expected result

A successful request returns OpenAI-compatible JSON.

Look for a choices[0].message.content value. If the model is rejected, refresh the model list and retry with its exact ID.

For streaming, tool calls, and production error handling, continue with the dedicated guides in the sidebar.