| Output $/MTok | $0.28 | $0.40 |
|---|---|---|
| Input $/MTok | $0.14 | $0.10 |
| Cached input $/MTok | $0.0028 | $0.0250 |
| Context window | 1,048,576 | 1,048,576 |
| Output cap | 384,000 | 8,192 |
| Modalities | in: text / out: text | in: text, image, audio, video / out: text |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Family | DeepSeek V3 | Gemini 2.0 |
| Knowledge cutoff | — | 2024-08-31 |
| Verified | 2026-05-18 | 2026-05-26 |
| Source | provider page ↗ | provider page ↗ |
| $/min | $0.004000 |
|---|---|
| $/min batch | — |
| Streaming | ✓ |
| Realtime | ✓ |
| Languages | 55+ |
| Diarization | included |
| TTFW | — |
| Verified | 2026-05-19 |
| Source | provider page ↗ |
| $/1M chars | $50.00 |
|---|---|
| Voice quality | neural |
| Voice cloning | ✓ included |
| Voice count | — |
| Languages | 31+ |
| SSML support | — |
| TTFB | — |
| Output formats | — |
| Verified | 2026-05-19 |
| Source | provider page ↗ |