OpenAI

OpenAI: GPT-4 Turbo (older v1106)

Type
language model
Context
128K tokens
Max output
4K
Released
6 November 2023
API string
openai/gpt-4-1106-preview

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Kilo Code $10 $30 31 Jul 2026
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 French 1,281.47 1,260–1,303 — —
Arena Score in English 1,277.26 1,272–1,282 — —
Arena Score, mathematics 1,269.24 1,261–1,277 — —
Arena Score, overall 1,263.6 1,260–1,267 — —
Arena Score in Spanish 1,260.22 1,238–1,282 — —
Arena Score, multi-turn dialogue 1,256.72 1,249–1,264 — —
Arena Score, programming 1,254.49 1,247–1,262 — —
Arena Score in Russian 1,250.44 1,241–1,260 — —
Arena Score, creative writing 1,244.68 1,237–1,253 — —
Arena Score, hard prompts 1,241.51 1,236–1,248 — —
Arena Score, instruction following 1,241.07 1,235–1,247 — —
Arena Score, long queries 1,236.28 1,228–1,245 — —
Arena Score, expert questions 1,210.87 1,199–1,223 — —
MATH, difficulty level five 40.02 % · with a tuned harness Epoch evaluations