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 | Muse Spark 1.2 Best option | DeepSeek V4 Flash 0731 Best option | MiniMax H3 Best option | Gemini Robotics ER 2 Preview Best option |
|---|---|---|---|---|
| Input Text Tokens | $1.25 | $0.07 | - | $1.00 |
| Output Text Tokens | $4.25 | $0.14 | - | $5.00 |
| Cached Read Audio Tokens | - | - | - | $0.10 |
| Cached Read Image Tokens | - | - | - | $0.10 |
| Cached Read Text Tokens | $0.15 | $0.00 | - | $0.10 |
| Input Image | - | - | $40,000.00 | - |
| Input Image Tokens | - | - | - | $1.00 |
| Input Audio Seconds | - | - | $0.00 | - |
| Input Audio Tokens | - | - | - | $1.00 |
| Input Video Seconds | - | - | $90,000.00 | - |
| Input Video Tokens | - | - | - | $1.00 |
| Output Video Seconds | - | - | $90,000.00 | - |
| Native Web Search Requests | $2,500.00 | - | - | - |
API provider availability and subscription plans.
