Inception · Efficient

Mercury 2.5 Preview

Added Sep 1, 2026

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.

Limits
	Mercury 2.5 PreviewInceptionThis model	Doubao Seed 2.0 MinidoubaoRemove
Provider	Inception	doubao
Discovery tier	Efficient	Efficient
Added	Sep 1, 2026	Feb 14, 2026
Context window	260KBest	256K
Max output	65.54KBest	32K
Average output	1.2K tokens	—
Pricing, USD per 1M tokens
Input	$0.04Best	$0.0493
Output	$0.15Best	$0.48
Cache read	$0.004	—
Performance
Request success (24h)	100.0%	—
Capabilities
Reasoning	Yes	No
Tools	Yes	No
Structured output	Yes	No
Parallel tools	Yes	No
Reasoning effort	none, low, medium, high	—

Public evaluations

Benchmarks

There are no public benchmark results for these models yet.

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.