Inference Economics
The cost and capability of AI models, over time.
Benchmark scores
One row per evaluated configuration. Scores use their own scales; — means unavailable and * means estimated.
Loading…
Performance
Task-weighted score
Cost per task
Task-weighted listed cost
Model families
Share of OpenRouter tokens
Seven-day average.
Average cost per equivalent task for model providers
Task-weighted · seven-day average.
Estimated task-equivalent volume by model family
Estimated tasks · seven-day average.
Estimated listed revenue by model family
Listed-price estimate · seven-day average.
Rentable-GPU inference spread
Test a transparent GPU-hour scenario against inference token revenue.
Revenue capacity vs. utilization
Maximum token revenue per GPU-hour; observed rental asks are horizontal hurdles.
Gross spread vs. H100 rental price
How quickly the economics compress at different achieved utilization levels.
Historical inference revenue capacity
Measured throughput repriced at the historical OpenRouter Llama 3.3 70B listed floor.
Gross revenue capacity—not profit. Assumes all generated tokens sell at the listed floor and excludes CPU, RAM, storage, bandwidth, orchestration, failures, fees, support, and reserve capacity.
Cost per task over time
Custom
Capability and cost
Task-weighted OpenRouter model usage.
Inspect the underlying token price
Use this to understand one model's listed or realized endpoint floor.
Input and output price
Advertised endpoint price floor.