OpenAI

GPT-4o (2024-08-06)

by OpenAItext+image+file->text2 endpoints
Neura Intelligence Index
26.2/ 100
Rank
#272
Confidence
high
Benchmarks
9(23% coverage)

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. GPT-4o ("o" for "omni") is...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Prompt caching
Long context
File input
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
TextImageFile
Output
Text

Technical Specifications

Context Window
128K tokens
Max Output
16.4K tokens
Knowledge Cutoff
2023-10-31
Tokenizer
GPT
Content Moderation
Enabled
Uptime (24h)
9997.7%
Country
🇺🇸US
Release Date
August 6, 20242y

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_completion_tokensmax_tokenspredictionpresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_pweb_search_options

Benchmark Performance

general

BenchmarkScoreSource
MMMLU
81.4
verified
SimpleQA
38.2
verified

coding

BenchmarkScoreSource
SWE-bench Verified
33.2
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
70.1
verified
Humanity's Last Exam
5.3
verified

multimodal

BenchmarkScoreSource
MMMU
72.2
verified
MMMU-Pro
59.9
verified
CharXiv Reasoning
58.8
verified

agent

BenchmarkScoreSource
TAU-Bench Retail
60.3
verified

Performance Over Time

Pricing

Per 1M tokens
Input$2.50
Output$10.00
Cache read$1.25
Added
August 6, 2024
Last synced 9/19/2026