Gemma 4 31B TL3

TL3 Open weights

Dense multimodal reasoning for coding, visual analysis, and agents with 256K context

Pricing

Prices for this trust level. Prices are per 1M tokens.

Trust levels for this model
Trust Level Region Context Max outputInput / 1MCache / 1MOutput / 1M§203
TL3 FR — — 0.15 € 0.17 $ 0.075 € 0.083 $ 0.40 € 0.44 $ —

USD prices are converted from EUR at the ECB reference rate of 1 EUR = 1.1014 USD (2026-11-16). EUR prices are authoritative.

Prices as of 16.11.2026.

About this model

Gemma 4 31B is Google DeepMind's largest dense model in the Gemma 4 family, with 30.7B parameters and a 256K-token context window. It uses a dense transformer and hybrid attention that alternates local sliding-window and global attention layers to handle extended inputs. The instruction-tuned model accepts text and images, including video processed as image frames, and generates text. Built-in thinking and native function calling support multi-step reasoning, agentic workflows, code generation, and debugging. Its vision capabilities cover document and PDF analysis, charts, screenshots, OCR, and visual question answering. Pretrained on more than 140 languages, it supports multilingual applications. Released as open weights under Apache 2.0 for commercial use.

API

Model ID gemma4-31b-tl3 OpenAI compatibleAnthropic compatible

Base URL https://api.aki.io/v1

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_AKI_API_KEY",
    base_url="https://api.aki.io/v1",
)

response = client.chat.completions.create(
    model="gemma4-31b-tl3",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_AKI_API_KEY",
  baseURL: "https://api.aki.io/v1",
});

const response = await client.chat.completions.create({
  model: "gemma4-31b-tl3",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);
curl https://api.aki.io/v1/chat/completions \
  -H "Authorization: Bearer $AKI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma4-31b-tl3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently Asked Questions

How much does Gemma 4 31B TL3 cost?
Input: 0.15 € per 1M tokens, Cache read: 0.075 € per 1M tokens, Output: 0.40 € per 1M tokens. Prices are exclusive of VAT.
What is the context window of Gemma 4 31B TL3?
Gemma 4 31B TL3 supports up to — tokens.
Which trust levels are available for Gemma 4 31B TL3?
Gemma 4 31B TL3 is available at TL3 (EU Resident, FR).
Is Gemma 4 31B TL3 open weights?
Yes. The model weights are available on Hugging Face under the linked license.
Is Gemma 4 31B TL3 available with zero data retention?
Yes. Gemma 4 31B TL3 is served at TL3 (EU Resident) with zero data retention and no model training.
How do I use Gemma 4 31B TL3 with the OpenAI SDK?
Use the model ID gemma4-31b-tl3 with the OpenAI-compatible endpoint at https://api.aki.io/v1.

Start Building with Gemma 4 31B TL3