Ultra-low-latency budget model engineered for high-frequency micro-tasks
| Scenario | Input Tokens | Output Tokens | Uncached Cost | With Prompt Caching |
|---|---|---|---|---|
| Short Chat Query | 1,000 | 500 | $0.00080 | $0.00070 |
| Document Summarization | 10,000 | 2,000 | $0.00440 | $0.00340 |
| Codebase & Context Analysis | 100,000 | 20,000 | $0.0440 | $0.0340 |
| Batch Corpus Processing | 1,000,000 | 100,000 | $0.3200 | $0.2200 |
Ideal for production workloads demanding budget capabilities, deep context depth (128k tokens), and reliability from OpenAI. Excellent when predictable tokenomics and prompt caching support are paramount.
If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.
For GPT-5.6 Luna, 1 million input tokens costs $0.20, while 1 million output tokens costs $1.20. If using prompt caching, repetitive input prefixes are discounted to $0.10 per million.
GPT-5.6 Luna features a maximum context window of 128,000 tokens (~96,000 words), with a maximum output limit of 16,384 tokens per completion.
GPT-5.6 Luna utilizes the OpenAI o200k_base (200k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.
Yes. GPT-5.6 Luna supports prompt caching with a cached input rate of $0.10/1M (saving up to 50% on repeated input context).