openai

OpenAI: GPT-4o

The OpenAI GPT-4o model is designed for various input types, including text, images, and files, with a maximum context length of 128,000 tokens. It supports tools integration but lacks reasoning capabilities. The output structure is not specified. For users who need to process large input data and can afford the price point, OpenAI GPT-4o might be worth considering. Its pricing model charges $2.5 per million input tokens and $10 per million output tokens. While its benchmark performance has a blended score of 31 across two independent benchmarks, including a score of 45.3 on Aider Polyglot, this may not be sufficient to justify its cost for users with more modest requirements or who prefer models with lower prices.

Quality Score
89/100
price + capability + benchmarks
Input Price
$2.50
per 1M tokens · checked 2026-09-07
Output Price
$10.00
per 1M tokens · checked 2026-09-07
Context Window
128,000
tokens

Benchmark results

Independent, published benchmarks. Blended score 31.0 across 2 benchmarks, last refreshed 2026-09-07. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 45.3
AI Index broad capability composite 9.0
Model ID
openai/gpt-4o
Vendor
openai
Released
May 2024
Tokenizer
GPT
Input Modalities
text, image, file
Output Modalities
text
Max Output
16,384 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
✓ accepts images
Audio
no
Moderated
yes

What it costs in practice

Computed from the current $2.50/M input and $10.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.09
Classify 1,000 customer emails 500k in / 50k out $1.75
A month of a busy support chatbot 5M in / 2M out $32.50

Similar models

Quick answers

How much does OpenAI: GPT-4o cost?
$2.50 per million input tokens and $10.00 per million output tokens.
What is OpenAI: GPT-4o's context window?
128,000 tokens, roughly 192 pages of text in a single request.
Does OpenAI: GPT-4o support tool calling?
It supports tool calling, structured output.
Can OpenAI: GPT-4o process images?
Yes, it accepts image input.