Loading the catalogue…
Google · Gemma
Gemma 4 26B A4B IT
Routed · non-EEA26B A4B (MoE) params262K contextOpen weightsapache-2.0€0.06 / €0.33 per 1MThinkingTool UseJSON Mode
Endpoints by sovereignty lane
1 activeSame model, one lane, your call. Sovereign first, then European-hosted, then routed (typically non-EU). Default endpoint per lane is highlighted.
Routed · 1
From €0.20 / M blended| Provider | Input / M | Output / M | Status |
|---|---|---|---|
GoogleDefault | €0.06 | €0.33 | Active |
Get started
OpenAI-compatible — drop in your slug
Stav speaks the same chat-completions API you already use. Set STAV_API_KEY and the curl below works. SDKs (openai-python, langchain, litellm) all work with the same base URL.
bash
curl https://api.stav.ai/v1/chat/completions \
-H "Authorization: Bearer $STAV_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-26b-a4b-it",
"messages": [{"role": "user", "content": "Hello!"}]
}'Prefer the Anthropic SDK contract? The same model is also reachable at POST /v1/messages — Stav's gateway translates between Anthropic-shape and the underlying provider for non-Claude models.
Sovereign-EU inference by default; the Smart Router lifecycle penalty drains traffic away from deprecating endpoints automatically. Add to attribute requests to a registered app.