Mercury 2
Mercury 2 is a chat model from Inception, released March 4, 2026. Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
by Inception · 128K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Mercury 2 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Inception API key. osFoundry discovers Mercury 2 automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Mercury 2 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Mercury 2 | Inception | — | 128K | $ 0.250 /1M | API only |
| Nemotron 3 Super | NVIDIA | — | 262K | $ 0.090 /1M | API only |
| LFM2-24B-A2B | LiquidAI | — | 33K | $ 0.030 /1M | API only |
| Aion-2.0 | AionLabs | — | 131K | $ 0.800 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Mercury 2
How much does Mercury 2 cost?
Mercury 2 is metered at $ 0.250 /1M for input, and $ 0.750 /1M for output. Bring your own Inception API key — osFoundry passes through provider pricing without markup.
Can I use Mercury 2 commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Mercury 2?
Mercury 2 supports a 128K token context window.
Can I run Mercury 2 locally?
No — Mercury 2 is hosted only and accessed via the Inception API.
What is Mercury 2 best at?
Mercury 2 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Mercury 2 in osFoundry?
Paste your Inception API key in the key dialog (or deploy the open weights for self-hostable models), assign Mercury 2 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Inception on March 4, 2026. Source: https://openrouter.ai/inception/mercury-2