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.
All unique meters observed across the selected models.
| Meter | GPT Realtime 2.1 Mini Best option |
|---|---|
| Input Text Tokens | $0.60 |
| Output Text Tokens | $2.40 |
| Cached Read Audio Tokens | $0.30 |
| Cached Read Image Tokens | $0.08 |
| Cached Read Text Tokens | $0.06 |
| Input Image Tokens | $0.80 |
| Input Audio Tokens | $10.00 |
| Output Audio Tokens | $20.00 |
API provider availability and subscription plans.
