Parameters
Undisclosed
Context Length
260K
Modality
Text
Architecture
Undisclosed
License
Proprietary
Release Date
31 Aug 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.04 · Output: $0.15
No evaluation benchmarks for Mercury 2.5 Preview available.
Overall Rank
-
Coding Rank
-
Mercury 2.5 Preview is an ultra-fast diffusion-based reasoning language model from Inception that refines multiple tokens in parallel. It is engineered for high-throughput reasoning, real-time code generation, and low-latency interactive workflows.
Architecture specifications are undisclosed for proprietary models.
The Mercury model family developed by Inception.
APX AI
Online