Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Listed rates
Price across providers
Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.
Lowest input$1.5/M
Across 15 priced providers
Median input$2/M
Midpoint of listed rates
Highest input$2.27/M
1.5× the lowest listed rate
Output range$4.5 – $6.8
Per million output tokens
Merge Gateway$1.5/MLowest
OpenCode Zen$2/M
xAI$2/M
Kilo Gateway$2/M
Eden AI$2/M
NanoGPT$2/M
Vercel AI Gateway$2/M
OpenRouter$2/M
LLM Gateway$2/M
CrossModel$2/M
GitHub Copilot$2/M
Abacus$2/M
Perplexity Agent$2/M
Eden AI$2/M
Venice AI$2.27/M
Cost calculator
Estimate a workload
$0.00
Excludes taxes, non-token charges, and tiered discounts.
Specification
Capabilities
Recorded from the source catalog and provider listings.
Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.
Merge Gateway
xAI
OpenRouter
LLM Gateway
CrossModel
GitHub Copilot
Abacus
Perplexity Agent