About
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
Related Models
Pricing
Input
$1.75
per 1M tokens
Output
$14.00
per 1M tokens
Blended
$4.81
per 1M tokens
Cheaper than 11% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$4.81
Monthly
$144.38
vs. Similar Models
Xiaomi: MiMo-V2.5-ProQ:0.0
$0.54-89%
Kimi K2.7 CodeQ:-0.3
$1.43-70%
Claude Opus 4.7 (Non-reasoning, High Effort)Q:+0.5
$10.00+108%
Kimi K2.6Q:+0.6
$1.35-72%
Performance
85
tokens/sec
Faster than 45% of models
67.72
seconds
Faster than 1% of models
67.72
seconds
Faster than 3% of models
Market Median
94 tok/s
9% slower
Median TTFT
1.11s
5984% slower
Throughput/Dollar
18
tok/s per $/1M
Speed Comparison
North Mini Code
85 tok/s+0%
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
85 tok/s-0%
Llama 3.2 Instruct 1B
86 tok/s+0%
Context Window
400K
tokens
Larger than 76% of models
Max Output
128K
tokens
32% of context
Benchmarks
MMLU-Pro
87.4%
GPQA Diamond
90.3%
HLE
35.4%
LiveCodeBench
88.9%
SciCode
52.1%
TerminalBench Hard
47.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
99.0%
IFBench
75.4%
Long Context Recall
72.7%
Tau2
84.8%
Market AverageTop Score