Models / Inception
Mercury 2
by Inception ·
inception/mercury-2Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
reasoningtool-usereleased 2026-03-04
Legal score · raw
-
not yet benchmarked
Context
128K
max output 50K
Input
$0.31
per 1M tokens
Output
$0.94
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.03
10x cheaper than uncached
Uncached input
$0.31
per 1M tokens
Capabilities
Modalities
in text
out text
Request parameters it accepts
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetools
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.