Mercury 2

Name: ARMES
Availability: InStock
Author: ARMES

— | Speed-critical inference, real-time applications, rapid response scenarios

Run Mercury 2

Included on FREE plan

Context Window

128K

Input Token Price

$0.25

per 1,000,000 tokens

Output Token Price

$0.75

per 1,000,000 tokens

Speed Rating

Ultra

Ultra Fast (>1,000 t/s)

Architectural Profile & Capabilities

— | Speed-critical inference, real-time applications, rapid response scenarios

Architecture Type: Diffusion LLM

Iterative diffusion denoising language model generating tokens non-autoregressively with ultra-high throughput.

Recommended Workloads & Primary Use Cases

Everyday reasoning

Drafting

Fast problem solving

ARMES Zero Data Retention

Calls to Mercury 2 are routed through strict Zero Data Retention inference channels. Prompts and outputs are never stored, indexed, or monitored by Inception.

View Privacy Architecture

More Models from Inception

Compare other engines available in this laboratory.

View Roster (2)

Mercury 2.5Free Tier

Inception's flagship 260K-context diffusion LLM (dLLM), generating and refining text in parallel at over 1,100 tps for real-time agents, code synthesis, and structured workflows accessible with Zero Data Retention on ARMES.

260K ctx$0.20/M