| Output $/MTok | $2.50 | $8.00 | $5.00 |
|---|---|---|---|
| Input $/MTok | $0.30 | $2.00 | $1.00 |
| Cached input $/MTok | $0.0300 | $0.5000 | — |
| Context window | 1,048,576 | 200,000 | 1,048,576 |
| Output cap | 65,536 | 100,000 | 65,536 |
| Modalities | in: text, image, audio, video / out: text | in: text, image / out: text | in: text / out: text |
| Tool use | ✓ | ✓ | ✓ |
| Structured output | ✓ | ✓ | ✓ |
| Family | Gemini 2.5 | o-series | Qwen 3 Coder |
| Knowledge cutoff | 2025-01-31 | 2024-06-01 | — |
| Verified | 2026-05-26 | 2026-05-17 | 2026-05-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |
| $/min | $0.002500 |
|---|---|
| $/min batch | — |
| Streaming | — |
| Realtime | — |
| Languages | 99+ |
| Diarization | extra-cost |
| TTFW | — |
| Verified | 2026-05-05stale 32d |
| Source | provider page ↗ |
| $/1M chars | $30.00 |
|---|---|
| Voice quality | neural |
| Voice cloning | — |
| Voice count | 94 |
| Languages | en |
| SSML support | — |
| TTFB | 100ms |
| Output formats | — |
| Verified | 2026-05-19 |
| Source | provider page ↗ |