Side-by-side technical and economic comparison between OpenAI's GPT-5.6 Terra and OpenAI's GPT-5.6 Luna.
| Metric | GPT-5.6 Terra | GPT-5.6 Luna | Advantage |
|---|---|---|---|
| Provider Organization | OpenAI | OpenAI | — |
| Standard Input / 1M | $2.00 | $0.20 | GPT-5.6 Luna (90% lower) |
| Cached Input / 1M | $0.20 | $0.02 | GPT-5.6 Luna lower |
| Output / 1M | $12.00 | $1.20 | GPT-5.6 Luna lower |
| Context Window | 1.05M | 1.05M | Equal |
| Max Generation Tokens | 16.4k | 16.4k | GPT-5.6 Terra |
| Tokenizer Family | OpenAI o200k_base (200k vocabulary) | OpenAI o200k_base (200k vocabulary) | — |
Opt for GPT-5.6 Terra when your engineering requirements prioritize OpenAI's ecosystem, specific tokenizer efficiencies (Exact BPE (o200k_base)), or when your expected prompt-to-completion ratios favor its $2/M input rate.
Opt for GPT-5.6 Luna when looking for OpenAI's tooling integration, specific context window depth (1.05M tokens), or when output generation volume favors its $1.2/M rate.