About
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
Related Models
Pricing
Input
$2.00
per 1M tokens
Output
$8.00
per 1M tokens
Blended
$3.50
per 1M tokens
Cheaper than 15% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.50
Monthly
$105.00
vs. Similar Models
Google: Gemma 4 26B A4B Q:-0.1
$0.13-96%
GPT-5.4 nano (medium)Q:-0.2
$0.46-87%
Grok 4.1 Fast (Reasoning)Q:+0.2
$0.28-92%
OpenAI: GPT-5.1-Codex-MiniQ:+0.2
$0.69-80%
Performance
145
tokens/sec
Faster than 71% of models
5.90
seconds
Faster than 15% of models
5.90
seconds
Faster than 45% of models
Market Median
94 tok/s
54% faster
Median TTFT
1.11s
430% slower
Throughput/Dollar
42
tok/s per $/1M
Speed Comparison
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
145 tok/s-0%
Qwen3 30B A3B 2507 (Reasoning)
146 tok/s+0%
Mistral Small 3
146 tok/s+1%
Context Window
200K
tokens
Larger than 50% of models
Max Output
100K
tokens
50% of context
Benchmarks
MMLU-Pro
85.3%
GPQA Diamond
82.7%
HLE
20.0%
LiveCodeBench
80.8%
SciCode
41.0%
TerminalBench Hard
37.1%
MATH-500
99.2%
AIME
90.3%
AIME 2025
88.3%
IFBench
71.4%
Long Context Recall
69.3%
Tau2
80.7%
Market AverageTop Score