Models and pricing
Every model is billed at the vendor's official list price per token. Availability, latency and throughput are measured by the routing engine on real traffic. Pin what you use, compare up to four side by side.
Best for coding · 8Best for chat products · 5Most used this month · 10New this week · 18Cheapest with 1M context · 10Reasoning · 20Tool calling · 15Structured outputs · 15
20 of 20 models. Prices are official vendor list prices in USD per million tokens. Latency and throughput are medians observed on ElevenRouter over the last 7 days.