Enterprise DNAEnterprise DNA
LModelsLong context
I

Mercury 2.5

by Inception

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple t

Visit InceptionSubmit your build →
M2

Models

Mercury 2.5

Added 9 Sept 2026

#inception

Overview

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...

How to use / API access

Call via OpenRouter with model id `inception/mercury-2.5`.

  • openrouter · inception/mercury-2.5 Docs

OpenRouter id: inception/mercury-2.5

Benchmarks

  • Intelligence Index (artificial-analysis): 12.3 index

Notes

Mercury 2.5 is listed in the EDNA Models directory from the OpenRouter catalogue.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →

USAGE / OPENROUTER

How much Mercury 2.5 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
38.5B ▼5.4%
Requests, last 7 days
6.9M
Tool calls, last 7 days
856K
Intelligence score
12.3
Average cost per request
3.3¢
Price per million tokens
$0.04 in · $0.15 out
05B10B19 Sept: 5.9B tokens, 1.3M requests20 Sept: 4.8B tokens, 1.1M requests21 Sept: 6.1B tokens, 1.1M requests22 Sept: 7.9B tokens, 1.9M requests23 Sept: 7.5B tokens, 1.9M requests24 Sept: 7B tokens, 848K requests25 Sept: 7.3B tokens, 768K requests26 Sept: 9.5B tokens, 2.2M requests27 Sept: 3.6B tokens, 646K requests28 Sept: 3.9B tokens, 709K requests29 Sept: 5.1B tokens, 904K requests30 Sept: 6.9B tokens, 1.1M requests1 Oct: 5.7B tokens, 1M requests2 Oct: 7B tokens, 1.9M requests3 Oct: 3.9B tokens, 729K requests4 Oct: 3.2B tokens, 674K requests5 Oct: 7.2B tokens, 1.1M requests6 Oct: 6.5B tokens, 1.3M requests7 Oct: 7.8B tokens, 1.6M requests8 Oct: 5.7B tokens, 1.3M requests9 Oct: 8.7B tokens, 1.1M requests10 Oct: 3.1B tokens, 533K requests11 Oct: 2.8B tokens, 572K requests12 Oct: 4B tokens, 622K requests13 Oct: 7.9B tokens, 814K requests14 Oct: 8.6B tokens, 1M requests15 Oct: 7.4B tokens, 1.4M requests16 Oct: 7B tokens, 1.6M requests17 Oct: 8.1B tokens, 1M requests18 Oct: 4.6B tokens, 692K requests19 Oct: 3.5B tokens, 621K requests20 Oct: 3.8B tokens, 737K requests21 Oct: 4.2B tokens, 856K requests19 Sept3 Oct17 Oct21 OctSee where it ranks on the leaderboard →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Understand the capabilitiesRead the model guide ↗

Check the source

Price date: 2026-10-18. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 12.3 (2026-10-18) ↗
Compare this model with alternatives →