Modelflare vs AionRouter
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.
ModelflareAionRouter
What matters most to you
For Balanced, choose Modelflare
Modelflare100
AionRouter0
Main reasons
Integrity25%
Integrity: no data for at least one relay
Availability20%
Availability: no data for at least one relay
Value20%
Value: no data for at least one relay
Speed15%
Speed: no data for at least one relay
Price15%
Modelflare costs ¥3.29 per session, 86% less than AionRouter at ¥24.1
Cache5%
Cache: no data for at least one relay
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 intelligence——
Intelligence keptNot checkedNot checked
Question accuracyNot checkedNot checked
Cost
Value for money——
Cost per coding session¥3.29¥24.1
Input price¥1.494¥10.95
Output price¥7.47¥54.75
Cache discountNot providedNot provided
Performance
Time to first token1.79 s—
Availability, last 24 hours98.6%—
Samples146—
Route
Groupgemini-stableStandard
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.