| Output $/MTok | $10.00 | $6.00 |
|---|---|---|
| Input $/MTok | $1.25 | $1.20 |
| Cached input $/MTok | $0.1250 | — |
| Context window | 400,000 | 262,144 |
| Output cap | 128,000 | 32,768 |
| Modalities | in: text, image / out: text | in: text / out: text |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Family | GPT-5 | Qwen 3 Max |
| Knowledge cutoff | 2024-09-30 | 2025-06-30 |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |
| $/min | $0.002150 | $0.012500 |
|---|---|---|
| $/min batch | — | $0.010170 |
| Streaming | ✓ | ✓ |
| Realtime | ✓ | ✓ |
| Languages | 56+ | 100+ |
| Diarization | included | included |
| TTFW | — | — |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |
| $/1M chars | $100.00 | $17.50 |
|---|---|---|
| Voice quality | neural | neural |
| Voice cloning | ✓ included | ✓ included |
| Voice count | — | 217 |
| Languages | 70+ | en, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or |
| SSML support | — | — |
| TTFB | — | 200ms |
| Output formats | — | pcm, mp3, wav, ulaw, alaw |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |