LLM Reference

Mercury 2

Researched 14d ago

Last refreshed 2026-05-22. Next refresh: weekly.

ProprietaryRAGLong contextClassificationJSON / Tool use

Mercury 2 is worth evaluating for rag, long context, and classification when its provider route and context window match the workload.

Decision context: RAG task fit, 2 tracked provider routes, and research from 2026-05-19.

Use it for

  • Teams evaluating rag, long context, and classification
  • Workloads that can use a 131k context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads

Cheapest output

$0.750

OpenRouter per 1M tokens

Provider routes

2

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-05-19

Researched 14d ago

fresh

Top use-case fit

RAG

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Classification

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 2
ProviderInput / 1MOutput / 1MCacheRoute
OpenRouter$0.250$0.750-
Serverless
Vercel AI Gateway$0.250$0.750read $0.025
Serverless

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

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.

Mercury 2 is a proprietary model in the Mercury family. The structured metadata tracks a 131k-token context window and structured outputs. This page tracks provider routes through OpenRouter and Vercel AI Gateway, with the cheapest tracked route listed at $0.25 input and $0.75 output per 1M tokens. No headline benchmark score is tracked for Mercury 2 yet.

Capabilities

Structured Outputs

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