openai

OpenAI: GPT-4o (2024-05-13)

GPT-4o from OpenAI is an advanced AI model with a context length of 128,000 tokens and support for text, image, and file inputs. It can handle multiple modalities but lacks reasoning capabilities and structured output formats; however, it does integrate tools. While its benchmark scores are robust, coming in at 14.2 on the AI Index and a strong 40.0 on coding tasks, GPT-4o is not free, with pricing at $5.0 per million input tokens and $15.0 for outputs. Given these costs and its blended benchmark score of 23.3 across two independent benchmarks, it may be more suitable for projects requiring specific modalities but where the cost is justified by the need for extensive text or coding tasks.

Quality Score
86/100
price + capability + benchmarks
Input Price
$5.00
per 1M tokens
Output Price
$15.00
per 1M tokens
Context Window
128,000
tokens

Benchmark results

Independent, published benchmarks. Blended score 23.3 across 2 benchmarks, last refreshed 2026-07-22. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 14.2
AI Index Coding software engineering tasks 40.0
Model ID
openai/gpt-4o-2024-05-13
Vendor
openai
Released
May 2024
Tokenizer
GPT
Input Modalities
text, image, file
Output Modalities
text
Max Output
4,096 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 $5.00/M input and $15.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.17
Classify 1,000 customer emails 500k in / 50k out $3.25
A month of a busy support chatbot 5M in / 2M out $55.00

Similar models

Quick answers

How much does OpenAI: GPT-4o (2024-05-13) cost?
$5.00 per million input tokens and $15.00 per million output tokens.
What is OpenAI: GPT-4o (2024-05-13)'s context window?
128,000 tokens, roughly 192 pages of text in a single request.
Does OpenAI: GPT-4o (2024-05-13) support tool calling?
It supports tool calling, structured output.
Can OpenAI: GPT-4o (2024-05-13) process images?
Yes, it accepts image input.