#30
GPT-5.4 nano
OpenAI · Proprietary · Reasoning · 400K context
38/ 100 composite
Released 2026-03-17
Benchmark Scores by Category
Coding
58.3
Knowledge
54.9
Agentic
16.6
Math
44.5
Multimodal
16.4
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$0.2
per 1M tokens
Output
$1.25
per 1M tokens
Value Score
52.8
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: