openai

OpenAI: GPT-4o (2024-11-20)

GPT-4o from OpenAI boasts an impressive context length of 128,000 tokens and can process text, images, and files; however, it lacks support for reasoning or structured output. With a blended benchmark score of 17.3 across one independent test, GPT-4o is a robust model in terms of capabilities but comes with a cost: $2.5 per million input tokens and $10 per million output tokens. Given its higher price point compared to other models, it might be best suited for users who require extensive handling of diverse inputs or need specific functionalities like image processing without the need for real-time reasoning or structured outputs.

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

Benchmark results

Independent, published benchmarks. Blended score 17.3 across 1 benchmark, last refreshed 2026-08-13. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 18.2
Model ID
openai/gpt-4o-2024-11-20
Vendor
openai
Released
November 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 (2024-11-20) cost?
$2.50 per million input tokens and $10.00 per million output tokens.
What is OpenAI: GPT-4o (2024-11-20)'s context window?
128,000 tokens, roughly 192 pages of text in a single request.
Does OpenAI: GPT-4o (2024-11-20) support tool calling?
It supports tool calling, structured output.
Can OpenAI: GPT-4o (2024-11-20) process images?
Yes, it accepts image input.