Porten

gemma-4-26b-a4b-it

Run gemma-4-26b-a4b-it on Porten — EU-sovereign, OpenAI-compatible AI inference.

Specifications

Model ID	gemma-4-26b-a4b-it
Context window	262K tokens
Capabilities	chat, Tools / function calling, Vision (image input)
Availability	Provisioned on demand — the first request loads it (may take longer).
API compatibility	OpenAI Chat Completions (drop-in)
Data residency	EU-sovereign — runs on the Porten network in Europe

Pricing

Use gemma-4-26b-a4b-it with the OpenAI SDK

Point any OpenAI-compatible client at Porten — only the base URL and model change.

curl https://porten.ai/v1/chat/completions \
  -H "Authorization: Bearer $PORTEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b-a4b-it",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://porten.ai/v1", api_key="$PORTEN_API_KEY")

resp = client.chat.completions.create(
    model="gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)