Mercury 2 vs GPT-5.6 Luna
Side by side: price, limits, capabilities and real cost examples. Catalog data · checked Nov 16, 2026
Short answer
- Mercury 2 is about 1.2× cheaper than GPT-5.6 Luna for a typical mix of three parts input and one part output.
- GPT-5.6 Luna reads 8.2× more text per request (1.05M vs 128K tokens).
- Only GPT-5.6 Luna offers: image input, file input.
- A quality verdict needs a hands-on test. Neither model has completed our Hero suite yet, so this page compares facts, not output quality.
| Mercury 2Inception | GPT-5.6 LunaOpenAI | |
|---|---|---|
| Input price / 1M tokens | $0.25 | $0.2 |
| Output price / 1M tokens | $0.75 | $1.2 |
| Context window | 128K | 1.05M |
| Max output per answer | 50K | 128K |
| Released | Feb 2026 | Jul 2026 |
| Tool calling | Yes | Yes |
| Structured output | Yes | Yes |
| Reasoning mode | Yes | Yes |
| Image input | No | Yes |
| File input | No | Yes |
| Prompt caching | Yes | Yes |
| What it costs in practice | ||
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $0.388 | $0.46 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | $0.039 | $0.032 |
| 10,000 product descriptions300 input and 200 output tokens per text | $2.25 | $3 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $0.863 | $0.78 |
Green marks the better value in that row. Prices are first-party list prices in USD. Method.
