Mercury 2.5 Previewon Krater.ai
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
Released August 31, 2026
Specifications
Mercury 2.5 Preview at a glance
Context
260K tokens
Max output
65.5K tokens
Input
Text
Output
Text
Input price
$0.04 / 1M
Output price
$0.15 / 1M
Capabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Compare
Compare Mercury 2.5 Preview
Mercury 2.5 Preview vs Mercury 2
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).
Open comparisonMercury 2.5 Preview vs Mercury Coder
Mercury Coder is the first diffusion large language model (dLLM).
Open comparisonMercury 2.5 Preview vs Hy4 preview
Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.
Open comparisonFAQ
Questions about Mercury 2.5 Preview
Clear answers based on the model catalog and Krater access.
Use Mercury 2.5 Preview in your API
Connect with Krater's unified API.
Ready to use Mercury 2.5 Preview?
Access leading models in one focused workspace.