LLM ReferenceLLM Reference

Mercury 2 on OpenRouter

Mercury · Inception Labs

Serverless

Pricing

TypePrice (per 1M)
Input tokens$0.25
Output tokens$0.75

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

About Mercury 2

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.

Get Started

Model Specs

Released2026-02-20
Context131K