| Output $/MTok | $2.50 | $15.00 |
|---|---|---|
| Input $/MTok | $0.30 | $2.50 |
| Cached input $/MTok | $0.0300 | $0.2500 |
| Context window | 1,048,576 | 1,050,000 |
| Output cap | 65,536 | 128,000 |
| Modalities | in: text, image, audio, video / out: text | in: text, image / out: text |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Family | Gemini 2.5 | GPT-5.4 |
| Knowledge cutoff | 2025-01-31 | 2025-08-31 |
| Verified | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ |
| $/min | $0.010170 | $0.003300 |
|---|---|---|
| $/min batch | — | — |
| Streaming | — | — |
| Realtime | — | — |
| Languages | en, fr, de, es, it | en |
| Diarization | included | included |
| TTFW | — | — |
| Verified | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ |
| $/1M chars | $50.00 | $30.00 |
|---|---|---|
| Voice quality | neural | neural |
| Voice cloning | ✓ included | — |
| Voice count | — | 94 |
| Languages | en, fr, de, es, pt, zh, ja, ko | en |
| SSML support | — | — |
| TTFB | 90ms | 37ms |
| Output formats | — | — |
| Verified | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ |