Is Mercury available on FastMetal?

Not at the moment. Mercury 2.5, from the same lab, is available on the FastMetal API today.

What is the context window of Mercury?

128,000 tokens, shared between the prompt and the response.

How does Mercury rank?

#261 on the public arena's Overall board (ELO 1,308). Ranks move as the leaderboard is updated.

Back to Models

inception/mercury

Not Available

Mercury

Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance. Mercury's speed enables developers to provide responsive user experiences, including with voice agents, search interfaces, and chatbots. Read more in the [blog post] (https://www.inceptionlabs.ai/blog/introducing-mercury) here.

6/26/2025

128,000 tokens

#228 Text (Coding)

Specifications

Modalities

Input

text

Output

text

Supported Parameters

frequency_penalty

max_tokens

presence_penalty

response_format

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_p

Max Output Tokens

16,384

Frequently asked questions

Is Mercury available on FastMetal?: Not at the moment. Mercury 2.5, from the same lab, is available on the FastMetal API today.
What is the context window of Mercury?: 128,000 tokens, shared between the prompt and the response.
How does Mercury rank?: #261 on the public arena's Overall board (ELO 1,308). Ranks move as the leaderboard is updated.