tokevenGPTvsGPT
GPT 5.6 Luna vs GPT 3.5 Turbo (0125)
Side-by-side comparison of pricing, task quality, and projected cost at higher scale.
Pricing
Side-by-side pricing
GPT 5.6 Luna
Fast / BudgetGPT 3.5 Turbo (0125)
Fast / BudgetInput $/MTok
$0.20
$0.50
Output $/MTok
$1.20
$1.50
Cache discount
90% off
0% off
Context
922K
16.385K
Quality
Task confidence comparison
Confidence score from zero to one hundred by task type, where higher is better.
Code Generation
70
vs
0
Code Review
68
vs
0
Summarization
84
vs
0
Q&A
85
vs
0
Extraction
89
vs
0
Reasoning
63
vs
0
Classification
91
vs
0
Creative Writing
58
vs
0
GPT 5.6 Luna
GPT 3.5 Turbo (0125)
Guidance
When to use GPT 5.6 Luna vs GPT 3.5 Turbo (0125)
Choose GPT 5.6 Luna when...
- -Cost matters: 60% cheaper on input tokens
- -You need a larger context window (922K vs 16.385K)
Choose GPT 3.5 Turbo (0125) when...
- Similar performance; consider provider preference or ecosystem fit.
At scale
Cost at scale
Estimated cost assuming a seventy percent input and thirty percent output token split.
GPT 5.6 Luna
GPT 3.5 Turbo (0125)
100K tokens
$0.05Cheaper
$0.08
1M tokens
$0.82
$0.80Cheaper
10M tokens
$8.20
$8.00Cheaper
FAQ
When should I use GPT 5.6 Luna instead of GPT 3.5 Turbo (0125)?
GPT 5.6 Luna and GPT 3.5 Turbo (0125) perform similarly across all tracked tasks. Pick based on pricing and provider preference.
Is GPT 3.5 Turbo (0125) cheaper than GPT 5.6 Luna?
GPT 3.5 Turbo (0125) input costs $0.50/MTok, which is 150% more than GPT 5.6 Luna at $0.20/MTok.
What are the context window sizes for GPT 5.6 Luna and GPT 3.5 Turbo (0125)?
GPT 5.6 Luna has a 922K token context window. GPT 3.5 Turbo (0125) has a 16.385K token context window.
Go deeper on either model
Per-call cost calculators, provider lineups, and price history for both models on this page.
Other comparisons
How GPT 5.6 Luna and GPT 3.5 Turbo (0125) stack up against the rest of the field.
Track your real costs
Comparisons show estimated costs at list price. The dashboard reveals your real spend and savings.