OpenAI
gpt-4-turbo-2024-04-09
Made by OpenAI. Released 2024-04-09. Accessibility not recorded. Cheapest standard rate we hold: $30 per million output tokens, at long context.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| batch | text · long | $5 | $15 | — | seller |
| batch | text · short | $5 | $15 | — | seller |
| standard | text · long | $10 | $30 | — | seller |
| standard | text · short | $10 | $30 | — | 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 | 0.1±0.02 | 2026-07-15 | — |
| frontiermath tiers 1 3 v2 | Epoch AI | 0.0±0.00 | 2026-08-27 | — |
| gpqa diamond | Epoch AI | 0.5±0.03 | 2025-02-27 | — |
| math level 5near its ceiling | Epoch AI | 0.5±0.01 | 2025-02-27 | — |
| otis mock aime 2024 2025near its ceiling | Epoch AI | 0.1±0.02 | 2025-02-27 | — |
| forecastbench | collected by Epoch AI | 59.4 | — | — |
| metr time horizons | collected by Epoch AI | 6.6 | — | — |
| mmlu | collected by Epoch AI | 0.8 | — | — |
| simplebench | collected by Epoch AI | 0.3 | — | — |
| weirdml | collected by Epoch AI | 0.2 | — | — |
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