DeepSeek V4 Flash
deepseek/deepseek-v4-flashTextLiveFast and low-cost for high volume.
Input · 1M€0.40tokens you send
Output · 1M€1.20tokens you get back
Context–tokens per request
First token––
Your price against the official price
Save up to 20%Input · 1MOutput · 1MSaving
Official price at DeepSeek€0.40€1.20
Nexrouting · Standard€0.40€1.200%
Nexrouting · Eco€0.32€0.96−20%
Uptime · 30 days99.90%
Measured on our own gateway, per day.
Good fit for
- Chat, summaries and extraction
import osfrom openai import OpenAI client = OpenAI( base_url="https://api.nexrouting.com/v1", api_key=os.environ["NEXROUTING_API_KEY"],) reply = client.chat.completions.create( model="deepseek/deepseek-v4-flash", messages=[{"role": "user", "content": "Hello"}],)
Savings
What you save each month
EUR
The model you use most
Share of traffic on EcoEco is the same model on separate, cheaper capacity, which can be less available at busy times. Batch work and background jobs usually fit there.
You save per month€100€1,205 a year · 20% less than the official price
We compare with the provider's own official price. Standard costs the same; the saving comes from the Eco lane.
Get started