Gemma 4 31B IT

Gemma 4 31B IT is part of Google's open-weight Gemma family, instruction-tuned for chat, coding, and reasoning. The Gemma line is built on research from the Gemini program and tuned for efficient on-prem and single-GPU-class deployments. A strong pick when you want open weights with Google-lineage quality for self-hostable-class workloads or fine-tuning bases.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="google/gemma-4-31b-it",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)