Quickstart

Everything on AxForge speaks the OpenAI API shape. If you have used the OpenAI SDK, you already know this API — the only changes are the base URL, your key, and the model name. Five minutes, start to first streamed token.

1. Get a key

Keys are allocated from the waiting list — request access and we email you a key. Every key is pinned to an EU region; requests echo the region back so you can verify where inference ran.

2. Point your SDK at us

Python

# pip install openai — the official SDK, unchanged
from openai import OpenAI

client = OpenAI(
    base_url="https://api.axforge.ai/v1",
    api_key="YOUR_AXFORGE_KEY",
    default_headers={"x-axforge-region": "eu-se-1"},
)

curl

$ export OPENAI_BASE_URL=https://api.axforge.ai/v1
$ export AXFORGE_API_KEY=your-key

3. First completion

r = client.chat.completions.create(
    model="qwen3.8-27b-nvfp4",
    stream=True,
    messages=[{"role": "user", "content": "Hello from Stockholm"}],
)
for chunk in r:
    print(chunk.choices[0].delta.content or "", end="")

The model is Qwen3.8 27B at €0.29 / 1M input tokens and €1.77 / 1M output tokens (launch pricing), with a 65,536-token context. Streaming responses include usage.

4. What else is behind the same key

Capability	Endpoint	Model name
Chat, tools, vision	/v1/chat/completions	qwen3.8-27b-nvfp4
Embeddings (1024-dim)	/v1/embeddings	qwen3-embed
Image generation	/v1/images/generations	ernie-image-turbo
Image editing	/v1/images/edits	flux2-klein-4b
Speech to text	/v1/audio/transcriptions	whisper
Text to speech	/v1/audio/speech	piper
Music generation	/v1/audio/music	minimax-music3

Each has its own page in these docs with request and response shapes, measured latencies, and practical guidance.

Zero retention, verifiable

Prompts and completions are processed in memory in the EU — never written to disk, logged, retained, or used for training. Only request metadata (token counts, timestamps, status) is kept for billing. The commitment in full: axforge.ai/privacy.