Skip to contentGPT-5.5 mini
CurrentVerified ·
Cheaper, faster sibling of GPT-5.5 that keeps reasoning and tool use while trading a little quality for dramatically lower latency and cost.
profile normalized against the 47-model field
Context window· 1.05M of 1.05M100%
Max output· 128K of 272K47%
Output speed· 165 tok/s52%
Affordability· $3.60 / Mtok out98%
Capability breadth· 8 of 1173%
Capability switches · 8 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$0.60 / Mtok USD/Mtok
Cached input $/Mtok$0.06 / Mtok USD/Mtok
Output $/Mtok$3.60 / Mtok USD/Mtok
Performance
Output speed165 tok/s tok/s
Time to first token280 ms ms
Capabilities
Input modalitiesText, image
Tool / function useYes
API
API model IDgpt-5.5-mini
General
Knowledge cutoffJanuary 2026
Benchmarks
Sourced evaluation scores, each verified against its primary source.
GPQA Diamond
GPQA Diamond: 82.4%
SWE-bench Verified
SWE-bench Verified: 72.6%
AIME 2025
AIME 2025: 91.0%
LiveCodeBench
LiveCodeBench: 74.8%