Skip to content

Models

Gemma 4 31B

gemma-4-31b 🇮🇹 Italy

Gemma 4 31B di Google, la versione densa: più precisa del 26B sui compiti difficili, più lenta. Legge immagini oltre al testo. Contesto di 262.144 token, pesi a 4 bit (QAT) pubblicati da Google. Gira su NVIDIA L40S, in Italia. In servizio.

At a glance

PublisherGoogle
ArchitectureDense, 31 billion parameters
LicenceApache 2.0
Precision4 bits, w4a16 (QAT), as released by Google
Context262,144 tokens, prompt and answer together
Longest answermax_tokens up to 32,768
ReadsText and images
Calls toolsYes
JSON schemaYes
ReasonsNo, as served: it answers straight away.
Runs in🇮🇹 Italy
StatusLoaded: the first request answers without a start-up wait. Live state on Status.
Pricegemma-4-31b@l40s: € 0,300000 input · € 0,720000 output , per million tokens, excluding VAT. All prices

Use it

curl https://api.ai-tokens.it/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-31b",
    "messages": [{"role": "user", "content": "Summarise in one line: the meeting moves to Thursday at 10."}]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.ai-tokens.it/v1", api_key=os.environ["API_KEY"])
answer = client.chat.completions.create(
    model="gemma-4-31b",
    messages=[{"role": "user", "content": "Summarise in one line: the meeting moves to Thursday at 10."}],
)
print(answer.choices[0].message.content)

More in Quickstart and Chat completions.

Limits

  • Prompt and answer together stay within 262,144 tokens; beyond that the engine refuses the request with a 400 that says so.
  • Served at 4 bits, which makes it faster and fits our machines; we write the precision of every model.
  • A request goes only to the zones your key allows; if the model has no machine there now, a 503 names the zones. It is never sent elsewhere.

Search the docs

Type to search…