LLM ReferenceLLM Reference

Mercury 2

Proprietary

About

Inception Labs' Mercury 2 is a commercial-scale diffusion-based language model (dLLM) released February 2026. Unlike autoregressive transformers, Mercury uses a diffusion architecture for faster inference. Designed for code generation, reasoning, and analysis tasks. Proprietary, available via the Inception API.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Rankings

Specifications

FamilyMercury
Released2026-02-20
Context131K

Created by

Inception Labs is an AI company building diffusion-based large language models (dLLMs), a fundamenta

San Francisco, CA
Founded 2024
Website