DeepSeek
AvailableDeepSeek V4 Pro
Large-context reasoning and coding with separate peak and off-peak pricing.
cache
Model pricing
-80%
Prices are shown per 1M tokens alongside their official reference rates. Your customer portal is authoritative for actual kineticRouter billing.
| Component | kineticRouter | Official reference |
|---|---|---|
| Input | $0.264/M | $1.32/M |
| Output | $0.792/M | $3.96/M |
| Cache read | $0.0088/M | $0.044/M |
| InputOff-peak hours | $0.132/M | $0.66/M |
| OutputOff-peak hours | $0.396/M | $1.98/M |
| Cache readOff-peak hours | $0.0044/M | $0.022/M |
API example
Use the OpenAI-compatible kineticRouter route with DeepSeek V4 Pro.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.kineticrouter.com/v1",
api_key=os.environ["KINETICROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)About this model
Large-context reasoning and coding with separate peak and off-peak pricing.
Model FAQ
Setup details for the shared OpenAI-compatible API.
How do I call this model?＋
Use deepseek/deepseek-v4-pro with the OpenAI-compatible https://api.kineticrouter.com/v1 base URL and your kineticRouter API key.