| Input per 1M tokens | $10 |
| Output per 1M tokens | $50 |
| Cache read per 1M tokens | $1 |
| Status | active |
| Source | official pricing page · verified 2026-08-06 |
1M context at standard pricing. Newer tokenizer produces ~30% more tokens for the same text than pre-4.7 Claude models.
Example costs
- One request (2,000 in / 500 out): $0.0450
- 100K such requests/month: $4,500
- 1M input + 1M output tokens: $60
Compare against other models →