Choose a model via the model field in your request. Each model runs on dedicated GPU hardware in Sweden.

Model	Vendor	Parameters	Context window	Vision
qwen3.6:35b-a3b	Alibaba	35B MoE	262,144	—
qwen3.5:9b	Alibaba	9.7B	262,144	—
gemma4:31b	Google DeepMind	31B	262,144	✓
bge-m3:latest	BAAI	568M	8,192	embedding
kb-whisper-large	Kungliga biblioteket	1.5B	—	audio (sv)

qwen3.5:35b-a3b is accepted as a backwards-compatible alias for qwen3.6:35b-a3b.

All chat models support streaming and tool calling. Only gemma4:31b has vision (16K context window for vision requests). The thinking aliases (qwen3.6:35b-a3b-thinking, qwen3.5:9b-thinking) are described under Chat completions.

The models are open weights that we host on our own hardware. KB-Whisper is the only model we run that was trained in Sweden.

List models programmatically

bash

curl https://api.staik.se/v1/models \
  -H "Authorization: Bearer sk-st-your-key"

json

{
  "data": [
    {
      "id": "qwen3.6:35b-a3b",
      "object": "model",
      "owned_by": "staik",
      "context_window": 262144,
      "capabilities": ["chat", "tools"]
    }
  ]
}

The response includes context_window and capabilities per model — useful for clients that configure themselves.

Your own GPUs (BYO): unmetered lane

If your organization has connected its own GPUs (Your GPUs), you choose the lane on the model name:

Prefixed — <org_slug>/<model> runs unmetered against your own hardware (no daily/hourly limit, no token deduction)
A bare model name goes to staik's shared pool and is metered against your plan

bash

# Unmetered: run against the organization's own GPU (prefix = your org slug)
curl https://api.staik.se/v1/chat/completions \
  -H "Authorization: Bearer $STAIK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "acme/qwen3.8:27b", "messages": [{"role": "user", "content": "Hi"}]}'

If your org has no healthy node serving the model you get a 503 — no silent fallback to staik. GET /v1/models lists your prefixed models. The prefix works the same on /v1/chat/completions and /v1/messages.

Models

List models programmatically

Your own GPUs (BYO): unmetered lane