modelgrep
O

OpenAI: GPT-4o (2024-08-06)

openai/gpt-4o-2024-08-06

129th smartest of 178ToolsJSONVision
Use via OpenRouter ↗
Intelligence
18.6
129th of 178
Design Elo
Speed
84
86th fastest
Latency
722ms
first token
Input price
$2.50
262nd cheapest
Context
128K
16K max out

How it compares

Smarter than28%
of all ranked models
Faster than71%
of all ranked models
Cheaper than12%
of all ranked models

Overview

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...

Benchmarks

independent · via OpenRouter
Artificial Analysis28th percentile
Intelligence Index
18.6
Coding Index
16.6
Agentic Index
9.7
GPQA Diamond
52%
Humanity's Last Exam
3%
SciCode
33%
Tau²-Bench (agentic)
29%

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Azure$2.50$10.00100%
OpenAI$2.50$10.00100%

Specifications

Context window128K
Max output16K
Knowledge cutoffOct 2023
Input modalitiestext, image, file
Output modalitiestext
Prompt caching
Cache read price$1.25/M
ModeratedNo

GPT-4o (2024-08-06) FAQ

How much does GPT-4o (2024-08-06) cost?

GPT-4o (2024-08-06) costs $2.50 per million input tokens and $10.00 per million output tokens via OpenRouter, making it 262nd cheapest of 298 paid models.

How smart is GPT-4o (2024-08-06)?

GPT-4o (2024-08-06) scores 18.6 on the Artificial Analysis Intelligence Index, ranking 129th of 178 benchmarked models, with a GPQA Diamond score of 52%.

How fast is GPT-4o (2024-08-06)?

GPT-4o (2024-08-06) generates around 84 tokens per second with 722ms time-to-first-token (p50), the 86th fastest tracked model.

What is GPT-4o (2024-08-06)'s context window?

GPT-4o (2024-08-06) supports a 128K-token context window and can output up to 16K tokens. It accepts text, image, file input.

Compare head-to-head