NOUMENOpen app
NOUMEN

Inception · Efficient

Mercury 2.5 Preview

Added Sep 1, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Mercury 2.5 Preview is Inception's latest and most intelligent diffusion language model. Instead of generating tokens strictly one at a time, it produces and refines multiple tokens in parallel, reaching up to 1,107 tokens per second on standard GPUs. It delivers a 10+ point intelligence gain over Mercury 2, with tunable reasoning, parallel tool calls, schema-aligned JSON output, and a 260K context window. It is built for latency-sensitive production work such as search agents, voice pipelines, customer support, rapid coding iteration, and coding subagents.

  • Reasoning
  • Tools
  • Structured output
  • Parallel tools
Input
Text
Output
Text
Reasoning effort
none · low · medium · high
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.04
Output
$0.15
Cache read
$0.004

Reference prices as published by the model provider. API example

Specifications

Context window
260K
Max output
65.5K
Average output (7 days)
1.2K tokens
Longer than 78% of 465 models

Side by side

Mercury 2.5 Preview compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Mercury 2.5 PreviewInceptionThis modelMercury 2InceptionRemove
ProviderInceptionInception
Discovery tierEfficientBalanced
AddedSep 1, 2026Jan 1, 2024
Limits
Context window260KBest128K
Max output65.54KBest50K
Average output1.2K tokens—
Pricing, USD per 1M tokens
Input$0.04Best$0.25
Output$0.15Best$0.75
Cache read$0.004Best$0.025
Performance
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index—10.8
Coding Index—31.1
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesYes
Parallel toolsYesNo
Reasoning effortnone, low, medium, high—

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Mercury 2.5 Preview
  • Mercury 2

Intelligence Index

  • Mercury 2.5 Preview—
  • Mercury 210.8
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Mercury 2.5 Preview: —
    • Mercury 2: 31.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Mercury 2.5 Preview: —
    • Mercury 2: 1.7%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Mercury 2.5 Preview: —
    • Mercury 2: 0.3%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Mercury 2.5 Preview: —
    • Mercury 2: 265 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Mercury 2.5 Preview: —
    • Mercury 2: 494 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Mercury 2.5 Preview: —
    • Mercury 2: 3.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Mercury 2.5 Preview: —
    • Mercury 2: 43.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Mercury 2.5 Preview: —
    • Mercury 2: 17.1%

  • GPQA Diamond

    Graduate-level science questions

    • Mercury 2.5 Preview: —
    • Mercury 2: 77.0%

  • IFBench

    Following precise output instructions

    • Mercury 2.5 Preview: —
    • Mercury 2: 69.8%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Mercury 2.5 Preview: —
    • Mercury 2: 0.0%

  • SciCode

    Scientific computing in Python

    • Mercury 2.5 Preview: —
    • Mercury 2: 37.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Mercury 2.5 Preview: —
    • Mercury 2: 26.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Mercury 2.5 Preview: —
    • Mercury 2: 70.8%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Mercury 2.5 Preview: —
    • Mercury 2: 43.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Prompt cache hits
0.0%
About $0.04 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inception/mercury-2.5-preview",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="inception/mercury-2.5-preview",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Inception

Other Inception models, starting with the same family.