Input/output modalities and key model metadata from the catalog.
30-day activity plus recent runtime. Text-first models use token volume; other modalities fallback to request activity.
Only benchmarks with comparable results across every selected model are shown.
Switch benchmark type to compare percent and numerical families separately.
Per-1M normalized pricing from observed provider tiers. Blended total uses 90% input + 10% output.
All unique meters observed across the selected models.
| Meter | Claude Opus 4.5 Best option |
|---|---|
| Input Text Tokens | $2.50 |
| Output Text Tokens | $12.50 |
| Cached Read Text Tokens | $0.25 |
| Cached Write Text Tokens | $3.13 |
| Cached Write Text Tokens 1h | $10.00 |
| Cached Write Text Tokens 5m | $6.25 |
| Native Web Fetch Requests | $500.00 |
| Native Web Search Requests | $2,500.00 |
API provider availability and subscription plans.
12 plans
Claude Team seat for collaborative workspaces with admin controls and shared team features.
Higher-usage Claude Team seat for collaborative workspaces.
Enterprise Claude workspace with custom usage, security, and administration controls.
Custom enterprise Perplexity plan for larger deployments with negotiated usage and support.
