Skip to content

Mercury 2

Mercury 2 is a diffusion-based reasoning language model developed by Inception Labs designed for ultra-low latency production AI applications.

Freemium · API

Mercury 2 in short

Mercury 2 delivers ultra-low latency for production AI apps, but its specialized architecture targets a narrow enterprise use case.
stork0:00 / 0:04
Ava, one of 89 voices. Press play.
A voiceover costs 5 cents a minute.
Type up to 20,000 characters, get an MP3. 89 voices, 38 languages. Three free a day, a minute each.
Make a voiceover

What is Mercury 2?

Mercury 2 is a diffusion-based reasoning language model developed by Inception Labs that enables AI developers and enterprise AI teams to create ultra-low latency production applications. It significantly reduces generation time while maintaining quality through parallel refinement strategies.

Key Features of Mercury 2

Mercury 2 leverages advanced diffusion technology for efficient language model capabilities.

  • Parallel token generation allowing simultaneous production of multiple tokens.
  • Tunable reasoning depth for adjustable output complexity.
  • Incorporates real-time voice interaction capabilities.
  • Supports interactive code editing and autocomplete functionalities.
  • Delivers rapid search capabilities in multi-hop retrieval tasks.

Who Should Use Mercury 2?

Mercury 2 is ideal for developers seeking speed and efficiency in AI-driven tasks. Its architecture allows for seamless integration in various applications.

  • AI developers needing rapid coding assistance.
  • Enterprise AI teams automating complex workflows.
  • Product builders designing interactive voice applications.

Mercury 2 Pricing & Plans

Mercury 2 operates on a token-based pricing model. The costs are as follows: $0.25 per 1 million input tokens and $0.75 per 1 million output tokens. The blended price is $0.38 per 1 million tokens.

  • Mercury 2: $0.25 per 1M input tokens, $0.75 per 1M output tokens.
  • Freemium access available for initial usage.

Mercury 2 vs Competitors

Mercury 2's diffusion approach offers distinct advantages in speed and controllability compared to traditional models.

Mercury 2

Freemium · API

From the Stork blog

Enjoying this? Get one like it in your inbox each morning.

one email a day · unsubscribe in two clicks · no third-party tracking