Products · Serverless Models
European AI API: serverless open models
Run leading open models through one OpenAI-compatible API, with serverless inference hosted in Stockholm, Sweden. AxForge operates the infrastructure, scaling and serving layer: no VM, no CUDA setup, no infrastructure management.
Get API access
Explore models
Every new account includes 3M free serverless tokens every 30 days. Your API key is created with your account and lives in the console.
What you get
One key, every served model
| API | OpenAI-compatible: chat, embeddings, images, audio and music on api.axforge.ai/v1. Streaming, tool calls, usage reporting. |
|---|---|
| Models | Qwen3.8 27B, Xev decisions, Qwen3 Embedding, ERNIE Image Turbo, FLUX.2 Klein edits, MiniMax Music 3, Whisper and Piper. See the full catalogue. |
| Pricing | Usage-based, in EUR, from €0.32 / 1M input tokens. All prices. |
| Region | Stockholm, Sweden (eu-se-1), pinned on the key; inference runs in-region. |
| Data | Zero prompt retention: prompts and completions are processed in memory and never stored. Trust Centre. |
First request
Five minutes to a completion
# your API key, from API Keys
export AXFORGE_API_KEY="YOUR_KEY"
curl https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen3.8-27b-nvfp4","messages":[{"role":"user","content":"Hello"}]}'# your API key, from API Keys
$env:AXFORGE_API_KEY = "YOUR_KEY"
$call = @{
Method = "Post"
Uri = "https://api.axforge.ai/v1/chat/completions"
Headers = @{ Authorization = "Bearer $env:AXFORGE_API_KEY" }
ContentType = "application/json"
Body = '{"model":"qwen3.8-27b-nvfp4","messages":[{"role":"user","content":"Hello"}]}'
}
(Invoke-RestMethod @call).choices[0].message.contentREM your API key, from API Keys
set AXFORGE_API_KEY=YOUR_KEY
curl.exe https://api.axforge.ai/v1/chat/completions ^
-H "Authorization: Bearer %AXFORGE_API_KEY%" ^
-H "Content-Type: application/json" ^
-d "{\"model\":\"qwen3.8-27b-nvfp4\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}"Need more?
When serverless is not the shape
A model you want that is not on the serverless API, traffic that needs its own hardware, or full control of the stack: that is a dedicated NVIDIA DGX Spark (GB10) from €0.85/hour, as Managed GPU or a GPU VM. The same hardware class the API runs on, with as much control as you want.
Related