OpenAI SDK integration

Use Gonka24 with the OpenAI SDK

Call Gonka24 with the official OpenAI Python and TypeScript SDKs using a custom base URL and Chat Completions.

Configuration verified August 31, 2026

Connection details

Every example on this page uses the same Gonka24 OpenAI-compatible endpoint, a dashboard API key, and a live model ID.

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"

Ready-to-use config

Python

Install with pip install openai and export GONKA24_API_KEY before running the script.

python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.gonka24.com/v1",
    api_key=os.environ["GONKA24_API_KEY"],
)

response = client.chat.completions.create(
    model="<model-id-from-/v1/models>",
    messages=[{"role": "user", "content": "Hello from Python"}],
)

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

TypeScript

Install with npm install openai. Keep this server-side so the API key is not bundled into browser code.

typescript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.gonka24.com/v1",
  apiKey: process.env.GONKA24_API_KEY,
});

const response = await client.chat.completions.create({
  model: "<model-id-from-/v1/models>",
  messages: [{ role: "user", content: "Hello from TypeScript" }],
});

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

Set up OpenAI SDK

Install the current official OpenAI SDK for Python or JavaScript/TypeScript.
Export GONKA24_API_KEY in your server or shell environment.
Fetch GET /v1/models and replace the model placeholder with an exact returned ID.
Run the example and read choices[0].message.content from the Chat Completions response.

What is supported

Supported

Models and Chat Completions

Use client.models.list() for discovery and client.chat.completions.create() for generation.

Supported

Streaming

Set stream: true and consume the SDK's stream iterator for OpenAI-compatible SSE chunks.

Supported

Function tools

The Chat Completions tools and tool_choice fields are supported when the selected model route supports tool calls.

Not included

Other OpenAI APIs

Responses, Assistants, Files, Images, Audio, Embeddings, Fine-tuning, and Realtime are not part of this verified Gonka24 integration.

Verify before an agent task

Fetch the model list and copy an exact model ID.
Send a short plain chat request through OpenAI SDK.
Confirm the request appears in your Gonka24 dashboard activity.
Only then enable tool use, file writes, or long-running agent work.

Troubleshooting

The SDK calls api.openai.com: Use base_url in Python or baseURL in TypeScript. The property names are intentionally different.

404 on chat completions: The client base must be https://api.gonka24.com/v1; the SDK appends /chat/completions.

responses.create() fails: Use chat.completions.create(). Gonka24 does not expose the OpenAI Responses API in this verified contract.

401 or model error: Confirm the environment variable is set, then refresh GET /v1/models and copy a live ID exactly.

Verification sources

Checked against the product documentation below and the Gonka24 public API contract on August 31, 2026.