Skip to content

Inceptionlabs · Chat

Mercury 2.5 Preview

InceptionlabsChatinception familyOne of its sources says the weights aren't publicly available.
From NanoGPT's listing:
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.
Market median price
$0.0675 blended / 1M
Max context
260K
Listings
2
Providers
2

Evidence and sources

All rankings: #397 on NanoGPT recentlySources: Models.dev data, NanoGPTPrimary data from Models.dev from NanoGPT: description

Advantages and trade-offs

Compared with 10 representative chat models

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured output

Listings

 Aihubmixmercury-2.5-previewSource: AIHubMix data docs260K$0.20cache read $0.02$0.75
 NanoGPTinception/mercury-2.5-previewSources: Models.dev data, NanoGPT260K$0.04cache read $0.004$0.15

Benchmarks

No benchmark scores yet.

Around the web

  • Terms of Use – Inception
    We are leveraging diffusion technology to develop a new generation of LLMs. Our dLLMs are …We are leveraging diffusion technology to develop a new generation of LLMs. Our dLLMs are much faster and more efficient than traditional ...

    inceptionlabs.ai

    Docs
  • Inception Labs
    Inception builds and deploys next‑generation large language models (LLMs) that are powered by diffusion rather …Inception builds and deploys next‑generation large language models (LLMs) that are powered by diffusion rather than traditional auto‑regressive generation.Read more

    inceptionlabs.ai

  • Inception
    Building the world's fastest language models, powered by diffusion. Website https://www.inceptionlabs.ai/ wood City, California 94063, …Building the world's fastest language models, powered by diffusion. Website https://www.inceptionlabs.ai/ wood City, California 94063, US. Labs Technology, ...

    linkedin.com

  • Inception Chat
    Chat with Mercury, the fastest commercial-grade diffusion LLM by Inception. Create a 2d zombie shooter …Chat with Mercury, the fastest commercial-grade diffusion LLM by Inception. Create a 2d zombie shooter game with powerups and weapons

    chat.inceptionlabs.ai

  • Inception (@_inception_ai) / X
    Pioneering a new generation of LLMs. Labs is the platform built to enable labs to …Pioneering a new generation of LLMs. Labs is the platform built to enable labs to monetize, distribute, and

    x.com

  • Introducing Mercury 2
    Mercury 2 — the world's fastest reasoning language model, built to make production AI feel …Mercury 2 — the world's fastest reasoning language model, built to make production AI feel instant. Price: $0.25/1M input tokens · $0.75/1M output tokens. ...

    inceptionlabs.ai

  • About – Inception
    Inception is an AI research and product company. We're building diffusion-based language models for production …Inception is an AI research and product company. We're building diffusion-based language models for production applications.Read more

    inceptionlabs.ai

  • Blog
    We are leveraging diffusion technology to develop a new generation of LLMs. Our dLLMs are …We are leveraging diffusion technology to develop a new generation of LLMs. Our dLLMs are much faster and more efficient than traditional autoregressive ...

    inceptionlabs.ai

  • Inception labs - Crunchbase Company Profile & Funding
    An AI startup that develops a new generation of large language models (LLMs) based on …An AI startup that develops a new generation of large language models (LLMs) based on a technique called diffusion.

    crunchbase.com

Also known as: inception/mercury-2.5-preview

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works