Mercury 2 is a large language model from Inception with a 128k token context window.
- Strengths
- Mercury 2 handles long-form text and document-level reasoning across its full context window.
- Best for
- Tasks requiring extended context, such as analyzing long documents, multi-turn conversations, or code repositories.
- Limitations
- Mercury 2 uses sequential token generation; later releases like Mercury 2.5 Preview introduced parallel diffusion-based generation for potential speed improvements.
Input / 1M
$0.25
Output / 1M
$0.75
Cached input / 1M
$0.025
Context window
128K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $0.25 | $0.75 | $0.025 | Imported from OpenRouter | openrouter.ai |