Compare Models
GPT 5.4 (high)

Release Date: Mar 5, 2026

Developer OpenAI  🇺🇸
Context Window 1M
Max Output Tokens 128k
Token Costs (in/out) $2.50/15.00
Weights Private
Input Modalities

Accuracy

0.50 %

Avg. Cost (In/Out)

$ 2.50 / $ 15.00

Latency

15 min 58 s

Vals Index
BenchmarksAccuracyRankings
ProgramBench

0.0%

±0.50
13/47
Proprietary BenchmarksAcademic BenchmarksIndustry Partners
Vals
Default Provider : OpenAI
Temperature: Default
Top P: Default
Top K: Default
Max Output Tokens: 128,000
Reasoning Effort: high