Inception

Mercury 2

by Inceptiontext->text1 endpoint
Neura Intelligence Index
52.2/ 100
Rank
#172
Confidence
low
Benchmarks
3(8% coverage)

Overview

Mercury 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...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Stop sequences

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
128K tokens
Max Output
50K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
February 24, 20266mo

Supported Parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetools

Benchmark Performance

coding

BenchmarkScoreSource
SciCode
38
verified

math

BenchmarkScoreSource
AIME 2025
91.1
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
74
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.25
Output$0.75
Cache read$0.03
Added
March 4, 2026
Last synced 9/19/2026