Mercury 2.5 Preview

Name: Mercury 2.5 Preview
Price: 0.04 USD
Author: Inception

Inception🇺🇸 United States

active

Compare with other models →

Context window260K tokens

Input / 1M tokens$0.04

Output / 1M tokens$0.15

Version History

2.5-previewminorAugust 31, 2026

Mercury 2.5 Preview succeeds Mercury 2 with a claimed 10+ point intelligence improvement and parallel token generation via diffusion, reaching claimed throughput of 1,107 tokens/sec.

Coverage

model releaseInception

Inception Launches Mercury 2.5 Preview, a Diffusion LLM Claiming 1,107 Tokens/Sec

Inception released Mercury 2.5 Preview, a diffusion-based language model that generates tokens in parallel rather than sequentially, claiming throughput of 1,107 tokens per second on standard GPUs. The model is available on OpenRouter with a 260K context window and an 80% launch discount through September 8, 2026.

September 1, 2026 · 2:35 PM2 min read

Inception Mercury 2.5 diffusion LLM