by OpenAI

GPT-4 Turbo.

text closed 128K ctx Quality 86.4
Cheapest input
$10.0/M
on OpenAI API
Cheapest output
$30.0/M
on OpenAI API
Fastest
33 tok/s
on OpenRouter
Hosted equiv.
~$10.8/hr
@ 100 tok/s on OpenAI API
Capability snapshot

What it's best at.

General knowledge 86.4

Scores normalised against benchmark ceilings (100 = perfect). Coloured by tier — coral 80+ frontier, lavender 65+ strong, sage 50+ solid, slate below.

Benchmarks

Published scores.

Benchmark Score Source
MMLU 86.4 official ↗
Description

About GPT-4 Turbo.

GPT-4 Turbo was OpenAI's flagship for early-to-mid 2024 before GPT-4o + GPT-5 superseded it. Still widely deployed because of the price/performance and the years of prompt engineering tuned to its quirks. 128K context, JSON mode, function calling.

Context window

How much it can remember.

128K tokens ≈ 96,000 English words
4K 32K 128K 1M
Max output per call: 4K tokens
Capabilities

What it can do.

Vision input
· Audio input
· Video input
Function calling
· Tool use
JSON mode
Streaming
· Fine-tuning