The Open-Source AI Stack
RSS
All models

Models · gpt-4

GPT-4 Turbo

Proprietary OpenAI · 2024-04-09 · Proprietary

Announced at OpenAI DevDay on November 6, 2023 as a 128K-context, cheaper successor to the original GPT-4 endpoint. The gpt-4-turbo-2024-04-09 revision shipped as the general-availability version with vision support and a knowledge cutoff through December 2023.

Cost

$10.00 / Mtok input
$30.00 / Mtok output

OpenAI API · as of 2026-05-21

source ↗

Speed

27.8 tok/sec output
1240 ms TTFT

· as of 2026-05-21

source ↗

Architecture

tokens in Embedding vocab not disclosed × N layers Architecture not disclosed (proprietary or undocumented) Output projection tokens out
Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture
unknown
Total params
not disclosed
Active params
not disclosed
Context window
128K tokens
Attention
unknown
Position encoding
unknown
Post-training
rlhf
OSI-approved
no
Data released
no
Training code
not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

General reasoning

MMLU-Pro 69.4 as of 2026-05-21 source ↗

Code

LiveCodeBench 29.1 as of 2026-05-21 source ↗

Math

MATH 73.7 as of 2026-05-21 source ↗
AIME 2024 15.0 as of 2026-05-21 source ↗

Available quantizations

None. The weights are not distributed, so there are no public quantizations.

Notable innovations

  • · 128K context window at frontier quality
  • · Native vision input in the GA release
  • · Roughly 3x cheaper than original GPT-4

Sources