infery
← All models
Mercury 2

Mercury 2

mercury-2

Chat & Textby Inception

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). 128,000 token context window, maximum output of 50,000 tokens. Includes independent benchmarks from Artificial Analysis.

chatstreamingtoolsjson mode

Details

Accepts
text
Context window
128K tokens

Pricing

Input
31.25 cr / 1M tokens
Output
93.75 cr / 1M tokens
Cached input
3.13 cr / 1M tokens

Prices in credits (1 credit = $0.01).

Data schema

approximate

Input

FieldTypeDescription
promptrequiredstringThe text prompt.

Output

FieldTypeDescription
textstringGenerated text (choices[0].message.content).