OpenAI
gpt-3.5-turbo-0125
Made by OpenAI. Released 2024-01-25. Accessibility not recorded. Cheapest standard rate we hold: $1.50 per million output tokens, at long context.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| batch | text · long | $0.25 | $0.75 | — | seller |
| batch | text · short | $0.25 | $0.75 | — | seller |
| standard | text · long | $0.50 | $1.50 | — | seller |
| standard | text · short | $0.50 | $1.50 | — | seller |
per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.
What it scores, by house
| Benchmark | House | Score | Evaluated | Scaffold |
|---|---|---|---|---|
| chess puzzles | Epoch AI | 0.0±0.00 | 2026-08-07 | — |
| frontiermath tiers 1 3 v2 | Epoch AI | 0.0±0.00 | 2026-08-27 | — |
| gpqa diamond | Epoch AI | 0.3±0.02 | 2025-01-27 | — |
| math level 5near its ceiling | Epoch AI | 0.1±0.01 | 2025-01-27 | — |
| mystery game puzzles | Epoch AI | 0.0±0.02 | 2026-08-27 | — |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.0±0.02 | 2026-08-07 | — |
| dtbenchnear its ceiling | collected by Epoch AI | 0.5 | — | — |
| forecastbench | collected by Epoch AI | 50.4 | — | — |
| lmca | collected by Epoch AI | 9.7 | — | — |
| mmlu | collected by Epoch AI | 0.7 | — | — |
| weirdml | collected by Epoch AI | 0.0 | — | — |
These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.
What retires, and when
- deprecation — 2026-10-23
Every rate we hold · Why there is no single best model · Everything from OpenAI