Mercury 3 icon

Mercury 3

Mercury 3 is Inception’s flagship diffusion-based large language model for production applications that need fast responses, reasoning, and long-context processing. It supports OpenAI-compatible workflows and is aimed at browser agents, education, real-time search, customer support, and other latency-sensitive systems.

Mercury 3

Mercury 3 overview

Mercury 3 is a diffusion-based large language model from Inception for production applications that need both reasoning and low-latency responses. It is the flagship model in Inception’s Mercury portfolio and is positioned for multi-step systems where waiting on model output can compound across agent steps.

The model provides a 1-million-token context window and reports 1,068 tokens per second on NVIDIA GPUs. It is available through Inception’s API Platform and several external access routes, with an OpenAI-compatible API intended to fit existing LLM applications. Use cases described by Inception include browser agents, interactive education, real-time search, and customer support.

Key features

Diffusion-based generation

The model generates through a diffusion-based coarse-to-fine process rather than committing to output one token at a time, supporting fast inference for production workflows.

High-throughput inference

The published benchmark figure is 1,068 tokens per second on NVIDIA GPUs, with the site describing performance above 1,000 tokens per second for commercial GPU deployments.

Long context

Mercury 3 supports a 1-million-token context window, allowing applications to provide substantially larger inputs than the 260,000-token context reported for Mercury 2.5.

Compatible API workflow

The model is OpenAI API compatible and is supported through AISuite, LiteLLM, and LangChain, reducing changes required to connect an existing application.

Multiple deployment routes

The model is available through the Inception API Platform and third-party access routes including OpenRouter, Baseten, and Vercel. Enterprise routes include AWS Bedrock and Azure Foundry.

Production operations

Enterprise deployments can use dedicated capacity, autoscaling, configurable data retention, compliance controls, and service-level agreements, subject to the selected arrangement.

Use cases

  • Browser and web-navigation agents

    Browser-use agents can call the model at each navigation, research, or log-analysis step. Faster responses reduce accumulated waiting across multi-step agent workflows.

  • Interactive education

    Tutoring and education products can use the model for conversational voice assistance, grading, hints, definitions, and adaptive responses when students need immediate feedback.

  • Real-time search

    Search systems can process documents and return answers while a user remains engaged. Inception cites applications including real-time search agents and smart-glasses experiences.

  • Customer support

    Support systems can use Mercury 3 for conversational responses across chat, voice, and email, including workflows where response accuracy and task completion are important.

  • Production LLM applications

    Teams building production AI applications can connect through the OpenAI-compatible API or use enterprise deployment routes when they need capacity, scaling, governance, or retention controls.

Pros and Cons

Pros

  • Fast published inference at 1,068 tokens per second on NVIDIA GPUs.
  • 1-million-token context window for large prompts and multi-document workflows.
  • OpenAI API compatibility with support for AISuite, LiteLLM, and LangChain.
  • Access through Inception’s API Platform, model routers, cloud platforms, and enterprise deployment routes.
  • Enterprise options include dedicated capacity, autoscaling, configurable data retention, and compliance controls.

Cons

  • The published performance and quality figures are benchmark or partner-reported results and may vary by workload, serving configuration, and application design.
  • The source does not provide detailed information about model limitations, supported modalities, or output reliability for every task.
  • Launch pricing is promotional, so the discounted rates should not be assumed to be permanent.

FAQ

What is Mercury 3?

Mercury 3 is a diffusion-based large language model designed for production applications that need fast responses and reasoning capability.

How can teams access Mercury 3?

It is available through the Inception API Platform and OpenRouter, Baseten, and Vercel. Enterprise deployment options also include AWS Bedrock and Azure Foundry, while model routers include OpenRouter and Models.dev.

Can Mercury 3 fit into an existing LLM stack?

Mercury 3 is OpenAI API compatible and can be used through libraries including AISuite, LiteLLM, and LangChain. The source also describes it as a drop-in replacement for traditional LLM workflows.

How is Mercury 3 priced?

The published standard price is $0.20 per million input tokens and $0.70 per million output tokens. At launch, the site lists a 50% discount, making those rates $0.10 and $0.35 respectively; cached input tokens are listed at $0.02 per million, or $0.01 at the launch discount.

What enterprise controls are available?

Enterprise deployments support dedicated capacity, autoscaling, compliance controls, configurable data retention, service-level agreements, and support options. The enterprise page states that prompts and outputs are treated as customer data and are not used for training.

Quick Facts

Category
AI model / developer tool
Model type
Diffusion-based large language model
Context window
1 million tokens
Published speed
1,068 tokens per second on NVIDIA GPUs
API compatibility
OpenAI-compatible
Primary workflows
Browser agents, education, real-time search, and customer support