AI model · Inception
Mercury 2.5
Model ID: inception/mercury-2.5
- Input
- $0.04 per 1M tokens
- Output
- $0.15 per 1M tokens
- Context
- 260K tokens at once
- Max output
- 66K tokens per reply
- Released
- 8 Sep 2026 Inception
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- NoOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Sources
- Inception: Mercury 2.5 on OpenRouter — read 2 Oct 2026