Modelflare vs CheapRouter
One model on two relays: integrity, speed, price, cache and availability, plus intelligence adjusted for degradation and value for money, with advice for the priority you choose.
Which to choose
Five dimensions
Further out is better. Integrity is the share of intelligence kept; the other four are places among all relays of this model.
ModelflareCheapRouter
What matters most to you
For Balanced, choose Modelflare
Modelflare82
CheapRouter60
Main reasons
Integrity25%
Integrity: no data for at least one relay
Availability20%
CheapRouter was available 100.0% of the last 24 hours; Modelflare 98.7%
Value20%
Modelflare gives 125 points per unit of money, 51% more than CheapRouter at 82.7
Speed15%
Modelflare answers in 0.87 s, 88% faster than CheapRouter at 7.18 s
Price15%
Modelflare costs ¥0.44 per session, 34% less than CheapRouter at ¥0.66
Cache5%
Cache is close: Modelflare 95%, CheapRouter 95%
Key figures
Adjusted intelligence
Higher is better
Cost per coding session
2M input + 40k output tokens · Lower is better
Value for money
Intelligence points per ¥1 · Higher is better
All figures
Intelligence
Adjusted intelligence54.654.6
Intelligence kept100%Not checked
Question accuracy97% (90 questions)Not checked
Cost
Value for money12582.7
Cost per coding session¥0.44¥0.66
Input price¥0.1992¥0.3
Output price¥0.996¥1.5
Cache discount95%95%
Performance
Time to first token0.87 s7.18 s
Availability, last 24 hours98.7%100.0%
Samples14818
Route
Groupopenai-first-topupCodex促销分组-不降智
Data securityLevel 4Level 0
Adjusted intelligence = the model's published intelligence index × intelligence kept. Intelligence kept = the relay's question accuracy ÷ the highest accuracy among checked relays of the same model; under 10 questions, no adjustment. Value = adjusted intelligence ÷ cost per coding session. Gaps under a threshold count as close. Advice weighs the metrics by the chosen priority and is a guide only.