Skip to content
FluxCDNFluxCDN
esc

DeepSeek: DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.

Input
92,232 Toman/M tokens
Output
345,016 Toman/M tokens
Context
164K
Max output
147K
Published
Aug 21, 2025
Maker
DeepSeek

Free plan prices, in Toman at today's rate. Plans and prices

Price by plan

Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period.

PlanInputOutput
Free92,232345,016
Pro88,452330,876
Max84,672316,736

Capabilities

  • Text
  • Tools
  • JSON
  • Reasoning

What it takes and gives

Accepts
  • Text
Creates
  • Text

Call it

Pass deepseek/deepseek-chat-v3.1 as the model name, or let router/auto choose for you.

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://ai.fluxcdn.cloud/api/v1",
    api_key=os.environ["FLUXCDN_API_KEY"],
)

resp = client.chat.completions.create(
    model="router/auto",
    messages=[{"role": "user", "content": "Hello"}],
)

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