Skip to main content

GabForge AI Documentation

The GabForge AI API is fully compatible with the OpenAI SDK. Swap your base URL, keep your existing code, and gain access to a local-first, privacy-respecting inference backend — with seamless cloud fallback when you need it.

OpenAI Compatible

Use any OpenAI SDK — Python, Node.js, Go, or cURL. Change one line of configuration, nothing else.

Local-First

Primary inference runs on our gabforge-coder model (Qwen2.5-Coder-32B). Your data stays on our infrastructure.

Cloud Fallback

Under high load, requests automatically fall back to claude-sonnet-4-6. Transparent to your code.

Get started in 3 steps

1

Get your API key

Sign in to your dashboard, navigate to API Keys, and click Create new key. Copy the key — it is only shown once.

Go to Dashboard
2

Install the OpenAI SDK

The GabForge API is fully compatible with the official OpenAI Python package.

pip install openai
3

Make your first request

Point the client at the GabForge base URL and use your API key.

from openai import OpenAI

client = OpenAI(
    base_url="https://ai.gabforge.ai/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="gabforge-coder",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Explore the documentation

API Reference

Full endpoint documentation with request/response schemas and error codes.

Code Examples

Copy-ready code in Python, JavaScript, and cURL for common use cases.

Streaming Responses

Process tokens as they arrive for real-time chat and autocomplete experiences.

Available Models

Compare model capabilities, latency, and choose the right one for your workload.