aicentos vs Modelflare
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.
aicentosModelflare
What matters most to you
For Balanced, choose aicentos
aicentos44
Modelflare12
Main reasons
Integrity25%
Integrity: no data for at least one relay
Availability20%
Availability: no data for at least one relay
Value20%
aicentos gives 77.7 points per unit of money, 1007% more than Modelflare at 7.02
Speed15%
Speed: no data for at least one relay
Price15%
aicentos costs ¥0.66 per session, 91% less than Modelflare at ¥7.30
Cache5%
Cache is close: aicentos 95%, Modelflare 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 intelligence51.351.3
Intelligence keptNot checkedNot checked
Question accuracyNot checkedNot checked
Cost
Value for money77.77.02
Cost per coding session¥0.66¥7.30
Input price¥0.3¥3.32
Output price¥1.5¥16.6
Cache discount95%95%
Performance
Time to first token——
Availability, last 24 hours——
Samples——
Route
Groupcodexopenai-enterprise
Data securityLevel 0Level 4
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.