Mercury 2 vs Mercury 2.5
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | Mercury 2inception/mercury-2 | Mercury 2.5inception/mercury-2.5 |
|---|---|---|
| Maker | inception | inception |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.2625 | $0.042 Lower |
| Cached input per 1M tokens | $0.02625 | $0.0042 |
| Cache write per 1M tokens | Same as input | Same as input |
| Output per 1M tokens | $0.7875 | $0.1575 Lower |
| Context window | 128,000 tokens | 260,000 tokens Larger |
| Max output | 128,000 tokens Larger | 65,536 tokens |
| Capabilities | Reasoning, tool use | Reasoning, tool use |
| Takes | Text | Text |
| Returns | Text | Text |
| Zero data retention | Not on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2026-02-24 | 2026-09-08 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Mercury 2 | Mercury 2.5 |
|---|---|---|
| 1,000 tokens in, 200 out | $0.00042 | $0.000074 |
| 10,000 tokens in, 1,000 out | $0.003413 | $0.000578 |
| 100,000 tokens in, 4,000 out | $0.0294 | $0.00483 |