Skip to contentGPT-5.2 mini
LegacyVerified ·
The cost-efficient mini variant of the legacy GPT-5.2 generation, kept available for low-cost pinned workloads.
profile normalized against the 47-model field
Context window· 400K of 1.05M38%
Max output· 64K of 272K24%
Output speed· 150 tok/s47%
Affordability· $2.70 / Mtok out99%
Capability breadth· 7 of 1164%
Capability switches · 7 of 11
Reasoning mode
Tool / function use
Streaming
JSON mode
Structured outputs
Prompt caching
Fine-tuning
Web search
Code execution
Vision input
Audio input
Specifications
Every value carries a primary source and a verification date.
Pricing
Input $/Mtok$0.45 / Mtok USD/Mtok
Cached input $/Mtok$0.045 / Mtok USD/Mtok
Output $/Mtok$2.70 / Mtok USD/Mtok
Performance
Output speed150 tok/s tok/s
Time to first token320 ms ms
Capabilities
Input modalitiesText, image
Tool / function useYes
API
API model IDgpt-5.2-mini
General
Knowledge cutoffJune 2025
Benchmarks
Sourced evaluation scores, each verified against its primary source.
GPQA Diamond
GPQA Diamond: 71.8%
SWE-bench Verified
SWE-bench Verified: 58.4%
AIME 2025
AIME 2025: 80.2%