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.
Per-1M normalized pricing from observed provider tiers. Blended total uses 90% input + 10% output.
No providers found yet.
All unique meters observed across the selected models.
| Meter | GPT Realtime 2.1 Best option | Claude Sonnet 5 Best option | Gemini Omni Flash Preview Best option | Grok 4.5 Best option |
|---|---|---|---|---|
| Input Text Tokens | - | $1.00 | $1.50 | $2.00 |
| Output Text Tokens | - | $5.00 | $9.00 | $6.00 |
| Cached Read Text Tokens | - | $0.20 | - | $0.50 |
| Cached Write Text Tokens | - | $3.75 | - | - |
| Cached Write Text Tokens 1h | - | $4.00 | - | - |
| Cached Write Text Tokens 5m | - | $2.50 | - | - |
| Input Image Tokens | - | - | $1.50 | - |
| Input Audio Tokens | - | - | $1.50 | - |
| Input Video Tokens | - | - | $1.50 | - |
| Output Video Tokens | - | - | $17.50 | - |
API provider availability and subscription plans.
