About
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...
Related Models
Pricing
Input
$5.00
per 1M tokens
Output
$15.00
per 1M tokens
Blended
$7.50
per 1M tokens
Cheaper than 7% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$7.50
Monthly
$225.00
vs. Similar Models
Llama 3.3 Instruct 70BQ:0.0
$0.61-92%
Mistral Small 3.1Q:0.0
$0.14-98%
Qwen3 32B (Non-reasoning)Q:0.0
$0.26-97%
Llama Nemotron Super 49B v1.5 (Non-reasoning)Q:+0.1
$0.17-98%
Performance
126
tokens/sec
Faster than 63% of models
0.54
seconds
Faster than 84% of models
0.54
seconds
Faster than 89% of models
Market Median
94 tok/s
34% faster
Median TTFT
1.11s
52% faster
Throughput/Dollar
17
tok/s per $/1M
Speed Comparison
Nova 2.0 Pro Preview (medium)
127 tok/s+0%
GPT-4o (Aug '24)
128 tok/s+1%
Qwen3 VL 30B A3B (Reasoning)
124 tok/s-1%
Context Window
128K
tokens
Larger than 16% of models
Max Output
4K
tokens
3% of context
Benchmarks
MMLU-Pro
74.0%
GPQA Diamond
52.6%
HLE
2.8%
LiveCodeBench
33.4%
SciCode
30.9%
TerminalBench HardNot evaluated
MATH-500
79.1%
AIME
11.0%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score