Gemma 3 27B
google/gemma-3-27b-it
available
chat
hosted: global
zero_retention
Google's Gemini and Gemma lines pair very large context windows with aggressive price-performance. Flash variants suit high-volume, latency-sensitive traffic; Gemma is the open-weight branch.
Context window
98,304
tokens
Input
₹13.20
per million tokens
Output
₹22.80
per million tokens
Licence
varies
verify before production use
Call this model
from openai import OpenAI
client = OpenAI(
base_url="https://thaliai.in/api/v1",
api_key="thali-sk-...",
)
completion = client.chat.completions.create(
model="google/gemma-3-27b-it",
messages=[{"role": "user", "content": "Hello"}],
)
Works with any OpenAI SDK. Streaming, fallback lists and provider preferences are documented in the routing guide.
This model is served via global infrastructure. For workloads
that must stay in India, filter the catalog for
hosted_in: "in".