Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | googleGoogle: Gemini 3.8 Flash TTSRemove × | cloudflareCloudflare: Clef OmniRemove × |
|---|---|---|
| What’s different | Separates spoken text from delivery instructions; supports exactly two named speakers with ordered dialogue turns. | Scores typed questions over images, audio and video in one pass; can hear video soundtracks while inspecting sampled frames. |
| Date | Sep 23, 2026Released | Oct 9, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.045/ 1K charactersfal · all routes ↗ | $0.15 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Native Voice ↗Unversioned · provider native voices | 1,278.04 ↗Provider native voices · all categories · US + UK accents · 8 listed voicesIndependent result95% CI 1,264.04–1,292.04 · n=2,978 | Not reported |
Specifications | ||
| Context window | 32.8K | 65.5K |
| Max output | 16.4K | 59K |
| Parameters | — | — |
| Image input | Not reported | Supported |
| Audio input | Not reported | Supported |
| Video input | Not reported | Supported |
| Open weights | Not reported | Supported |