Model comparison
GPT-5.6 Terra vs GPT-5.6 Luna
Compare GPT-5.6 Terra vs GPT-5.6 Luna API pricing: input/output token costs, cache pricing, context windows, workload estimates, and routing fit.
GPT-5.6 Terra
openai · gpt-5.6-terra
- Input
- $2.5
- Output
- $15
- Context
- 1.1M
GPT-5.6 Luna
openai · gpt-5.6-luna
- Input
- $1
- Output
- $6
- Context
- 1.1M
Quick take
GPT-5.6 Luna has the lower input price at $1 per 1M input tokens. GPT-5.6 Luna is cheaper for the example blended workload below. GPT-5.6 Terra has the larger context window at 1.1M tokens.
Choose GPT-5.6 Terra if...
- GPT-5.6 Terra is a reasonable pick when its provider, latency, or integration path fits your stack better.
Choose GPT-5.6 Luna if...
- GPT-5.6 Luna is the better default for cost-sensitive traffic and repeated high-volume calls.
Example workload cost
Estimates use input tokens plus 20% output tokens. They exclude provider discounts, cache hits, and tool/search surcharges.
| Workload | GPT-5.6 Terra | GPT-5.6 Luna | Cheaper |
|---|---|---|---|
| 1M input + 200K output | $5.50 | $2.20 | GPT-5.6 Luna |
| 10M input + 2M output | $55.00 | $22.00 | GPT-5.6 Luna |
| 100M input + 20M output | $550.00 | $220.00 | GPT-5.6 Luna |
Context, output, and capability fit
GPT-5.6 Terra provides the larger context window. Check max output separately when the task needs long reports, code generation, or full-document rewrites.
- GPT-5.6 Terra max output
- 128K
- GPT-5.6 Luna max output
- 128K
- GPT-5.6 Terra features
- prompt caching, function calling, vision
- GPT-5.6 Luna features
- prompt caching, function calling, vision
Risk notes for GPT-5.6 Terra
- No major capability risk is flagged in this snapshot, but provider pages should still be verified before production routing.
Risk notes for GPT-5.6 Luna
- No major capability risk is flagged in this snapshot, but provider pages should still be verified before production routing.
Routing tags
frontierreasoningcodingagentslong-contextmultimodalcache-friendlyragbudgetfast