| Input per 1M tokens | $0.75 |
| Output per 1M tokens | $4.5 |
| Cache read per 1M tokens | — |
| Status | active |
| Source | official pricing page · verified 2026-08-06 |
Migration target for gpt-3.5-turbo and gpt-5-mini.
Example costs
- One request (2,000 in / 500 out): $0.0037
- 100K such requests/month: $375
- 1M input + 1M output tokens: $5.25
Compare against other models →