GPT-5.6 Luna
Pricing & Specs
OpenAI · $0.2 input / $1.2 output per 1M tokens · 1.05M context window
The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on GPT-5.6 Luna costs about $0.0008 — roughly $0.80 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.
GPT-5.6 Luna API Pricing
| Tokens | Price |
|---|---|
| Input | $0.2 / 1M tokens |
| Output | $1.2 / 1M tokens |
| Cached input | $0.02 / 1M tokens |
Prompts >272K tokens priced at 2x input, 1.5x output. Cache writes at 1.25x uncached input rate.
What that means in practice
GPT-5.6 Luna Specs
| Spec | Value |
|---|---|
| Context window | 1.05M tokens |
| Max output tokens | 128K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | February 16, 2026 |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | Yes |
Notes
Cost-optimized for high-volume workloads. Corresponds to nano tier from earlier GPT-5 families.
FAQ
How much does GPT-5.6 Luna cost?
GPT-5.6 Luna costs $0.2 per 1M input tokens and $1.2 per 1M output tokens ($0.02 per 1M cached input tokens).
What is GPT-5.6 Luna's context window?
GPT-5.6 Luna has a 1.05M-token context window. Maximum output is 128K tokens.
Can I test GPT-5.6 Luna on my own task?
Yes. OpenMark lets you benchmark GPT-5.6 Luna against 100+ models on your own task with real API calls — no API keys needed, free tier available.
Is GPT-5.6 Luna the right model for YOUR task?
Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.