Skip to content

Inceptionlabs · Chat

Mercury Coder Small

InceptionlabsChatMercury familyOne of its sources says the weights aren't publicly available.
From NanoGPT's listing:
Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.
Market median price
$0.4375 blended / 1M
Max context
33K
Listings
4
Providers
4

Evidence and sources

All rankings: #590 on NanoGPT recentlySources: GenAI Prices data, Models.dev data, NanoGPTPrimary data from GenAI Prices from Models.dev: name, weights availability 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, 04:34 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

Listings

 NanoGPTmercury-coder-smallSources: Models.dev data, NanoGPT33K$0.25cache read $0.125$1.00
 OpenRoutermercury-coder-small-beta · betaSource: GenAI Prices dataNot published by the provider$0.25$1.00
 Vercelinception/mercury-coder-smallSource: Helicone Costs dataNot published by the provider$0.25$1.00
 Vercel AI Gatewayvercel_ai_gateway/inception/mercury-coder-smallSource: LiteLLM data32K$0.25$1.00

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Reasoning

Data credits: LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence)

Around the web

  • Introducing Mercury, the World’s First Commercial-Scale Diffusion Large Language Model. – Inception
    title: Introducing Mercury, the World’s First Commercial-Scale Diffusion Large Language Model. – Inception description: We …title: Introducing Mercury, the World’s First Commercial-Scale Diffusion Large Language Model. – Inception description: We trained diffusion large language models that are up to 10x faster and cheape…

    inceptionlabs.ai

  • Introducing Mercury, our General Chat Diffusion Large Language Model – Inception
    title: Introducing Mercury, our General Chat Diffusion Large Language Model – Inception description: In February, …title: Introducing Mercury, our General Chat Diffusion Large Language Model – Inception description: In February, we announced Mercury Coder, the first commercial-scale diffusion large language model…

    inceptionlabs.ai

  • Blog – Inception
    Diffusion Models and the Personal Agent Era We evaluated Mercury 2 on PinchBench, the open-source …Diffusion Models and the Personal Agent Era We evaluated Mercury 2 on PinchBench, the open-source benchmark built on top of OpenClaw — the fastest-growing open-source project in GitHub history, with …

    inceptionlabs.ai

  • Mercury Diffusion LLM Now Available on Azure AI Foundry – Inception
    title: Mercury Diffusion LLM Now Available on Azure AI Foundry – Inception description: "Today, we're …title: Mercury Diffusion LLM Now Available on Azure AI Foundry – Inception description: "Today, we're thrilled to announce that Mercury is available on Azure AI Foundry, bringing the first commercial…

    inceptionlabs.ai

  • Inception – When Every Millisecond Matters
    We’re available through major cloud providers like AWS Bedrock and Azure Foundry. Talk with us …We’re available through major cloud providers like AWS Bedrock and Azure Foundry. Talk with us about fine-tuning and private deployments. Talk to Sales Integrate in seconds Our models are OpenAI API …

    inceptionlabs.ai

  • The Next Step for dLLMs: Scaling up Mercury – Inception
    value? We think so! For example, Mercury provides higher quality than Claude 4.5 Haiku at …value? We think so! For example, Mercury provides higher quality than Claude 4.5 Haiku at one-fifth the latency and less than one-quarter the price. What’s Next? This upgrade is a big leap, but it is…

    inceptionlabs.ai

  • Mercury 2 on Azure Foundry - Inception Labs
    title: Mercury 2 on Azure Foundry – Inception description: Mercury 2 is now available on …title: Mercury 2 on Azure Foundry – Inception description: Mercury 2 is now available on Azure AI Foundry, combining Inception’s diffusion architecture with Azure’s enterprise-ready infrastructure fo…

    inceptionlabs.ai

  • Introducing Mercury 2 – Inception
    title: Introducing Mercury 2 – Inception description: "Today, we're introducing Mercury 2 — the world's …title: Introducing Mercury 2 – Inception description: "Today, we're introducing Mercury 2 — the world's fastest reasoning language model, built to make production AI feel instant." published: "Jul 29…

    inceptionlabs.ai

  • More builders. More throughput. Better Mercury 2. – Inception
    with. 100M free tokens, up from 10M Every new Inception API key now includes 100 …with. 100M free tokens, up from 10M Every new Inception API key now includes 100 million free tokens. Enough headroom to benchmark Mercury against your current stack on production workloads. Start bu…

    inceptionlabs.ai

  • Our Models – Inception
    Choose the access plan that works best for your needs Free, Try our models., Access …Choose the access plan that works best for your needs Free, Try our models., Access all models, 10 million free tokens Get Started Developer, Scale our models., Usage-based pricing, Generous rate lim…

    inceptionlabs.ai

Also known as: inception/mercury-coder-small, mercury-coder-small-beta, vercel_ai_gateway/inception/mercury-coder-small

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