OpenAI
GPT-5.6 Luna pricing and benchmarks
The GPT-5.6 model optimized for cost-sensitive, high-volume workloads.
Input
$0.20
per 1M tokens
Cached input
$0.02
per 1M tokens
Output
$1.20
per 1M tokens
Capability index
156.3
#8 of 16 tracked
How capable is GPT-5.6 Luna?
GPT-5.6 Luna scores 156.3 on the Epoch Capabilities Index (confidence interval 154.1–158.9), ranking #8 of the 16 rated models we track. It is a best-value pick: no cheaper model we track scores higher.
| Benchmark | Tests | Score |
|---|---|---|
| GPQA Diamond | Science reasoning | 88.8% |
| FrontierMath (Tiers 1–3) | Advanced math | 82.1% |
| SimpleQA Verified | Factual accuracy | 41.0% |
| ARC-AGI-2 | Abstract reasoning | 59.5% |
| DeepSWE | Coding | 67.2% |
| APEX-Agents | Agentic work | — |
Source: Epoch AI (as “GPT-5.6 Luna”), best recorded result, CC BY 4.0. A dash means no published score. Compare all models
What GPT-5.6 Luna costs in practice
| Workload | Monthly cost |
|---|---|
Support chatbot 100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each. | $78.00 |
Document Q&A (RAG) 50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each. | $116.00 |
Coding agent 10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens. | $53.60 |
Pricing details
- Cache writes are billed at $0.25 per 1M tokens.
- Fast mode costs 2x the standard rate; Flex costs half.
Estimate your GPT-5.6 Luna bill
- GPT-5.6 LunaOpenAI$116.00/mo$0.0023 / request
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.