DeepSeek V3 (Turbo)
deepseek/deepseek-v3-turbo
available
chat
hosted: global
zero_retention
DeepSeek's models deliver near-frontier quality at a fraction of frontier pricing. R1 adds explicit long-form reasoning; V3 is the general-purpose workhorse.
Context window
64,000
tokens
Input
₹43.70
per million tokens
Output
₹142.60
per million tokens
Licence
varies
verify before production use
Call this model
from openai import OpenAI
client = OpenAI(
base_url="https://www.thaliai.in/api/v1",
api_key="thali-sk-...",
)
completion = client.chat.completions.create(
model="deepseek/deepseek-v3-turbo",
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".