OpenAI: GPT-4 Turbo (older v1106)

OpenAI: GPT-4 Turbo (older v1106)

openai · Released Nov 6, 2023
35
Our Score

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to April 2023.

$10.00 / 1M Input Price
$30.00 / 1M Output Price
128,000 tokens Context Window
4,096 tokens Max Output

Capabilities

Tool Use Function Calling Vision

Architecture

ModalityText → Text
TokenizerGPT

Performance Indices

Source: Artificial Analysis

25.6 Intelligence Index
21.8 Coding Index
34.7 Math Index

Benchmark Scores

Evaluations

GPQA Diamond 66.6%
Graduate-level scientific reasoning
HLE 4.6%
Humanity's Last Exam
MMLU Pro 80.6%
Multi-task language understanding
LiveCodeBench 45.7%
Live coding evaluation
SciCode 38.1%
Scientific computing
MATH 500 91.3%
Mathematical problem-solving
AIME 43.7%
Competition mathematics

Benchmark data from Artificial Analysis and Hugging Face

Model Information

OpenRouter ID openai/gpt-4-1106-preview
Provideropenai
Model FamilyGPT-4
Release Date November 6, 2023
Context Length128,000 tokens
Max Completion4,096 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $10.00 $0.010000
Output $30.00 $0.030000

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

541ms
Best Latency (TTFT)
4 tok/s
Best Throughput
0/1
Active Endpoints
Available via: OpenAI