OpenAI

GPT 4 Turbo 2024-04-09

Type
language model
Context
128K tokens
Max output
4K
API string
azure/gpt-4-turbo-2024-04-09

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Microsoft Foundry $10 $30 31 Jul 2026
OpenAI $10 $30 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in English 1,291.29 1,286–1,296 — —
Arena Score in French 1,274.31 1,253–1,296 — —
Arena Score, overall 1,271.85 1,268–1,276 — —
Arena Score, mathematics 1,271.63 1,264–1,279 — —
Arena Score, creative writing 1,268.88 1,261–1,277 — —
Arena Score, programming 1,268.83 1,262–1,276 — —
Arena Score, multi-turn dialogue 1,267.04 1,260–1,274 — —
Arena Score in Spanish 1,259.23 1,238–1,280 — —
Arena Score in Russian 1,258.49 1,250–1,267 — —
Arena Score, long queries 1,254.05 1,246–1,262 — —
Arena Score, hard prompts 1,251.2 1,245–1,257 — —
Arena Score, instruction following 1,249.88 1,244–1,255 — —
Arena Score, expert questions 1,222.84 1,212–1,234 — —
Arena Score, working with images 1,090 1,078–1,102 — —
MATH, difficulty level five 46.73 % · with a tuned harness Epoch evaluations
GPQA Diamond — graduate-level questions 28.79 % · with a tuned harness Epoch evaluations
WeirdML — unusual machine learning tasks 18.01 % — WeirdML Leaderboard
SimpleBench — trick questions 10.12 % — SimpleBench Leaderboard
Mock AIME 2024–2025 — olympiad problems 6.57 % · with a tuned harness Epoch evaluations
Chess puzzles 1.09 % — Epoch evaluations