# Mercury 2.5 Preview: AI model fact sheet

- **Provider:** inception
- **Released:** 2026-08-31
- **Context window:** 260,000 tokens
- **API pricing:** $0.04 / 1M input, $0.15 / 1M output
- **OpenRouter ID:** inception/mercury-2.5-preview
- **Capabilities:** conversation, reasoning, code-generation, analysis, tool-use, agentic-tool-use

Inception's diffusion language model generates and refines tokens in parallel instead of one at a time. It reaches a reported 1,107 tokens per second on standard GPUs, with a 260K-token context window and a claimed 10-point intelligence gain over Mercury 2.

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/mercury-2.5-preview