Gemini 3.6 Flash

Gemini 3.6 Flash is Google's latest fast-tier Gemini, tuned for agentic and coding workloads that need near-frontier quality at high throughput. It's more efficient than 3.5 Flash: producing roughly 17% fewer output tokens per task and priced lower on output, while keeping a very large 1M-token context window. Use it as a high-volume default for agents, coding assistants, and long-document tasks where cost per task matters.

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/gemini-3.6-flash",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

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