Mercury 2
InceptionProprietary
Description
Mercury 2 is the fastest reasoning LLM, built on diffusion-based language model (dLLM) architecture. Instead of generating text token-by-token, it refines multiple text blocks simultaneously, achieving over 1,000 tokens per second on Nvidia Blackwell GPUs — 5x faster than leading speed-optimized LLMs. Supports tool usage and JSON output with 128K context window.
Release Date
2026-02-20
Parameters
—
Context Length
128K
Modalities
text
Capability Radar
70
general
50
coding
60
reasoning
51
scienceest.
50
agents
0
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
Tau2 Airline
53.0%SR
Instruction Following
IFBench
71.0%SR
Math
AIME 2025
91.1%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
74.0%SR
LiveCodeBench
67.0%SR
SciCode
38.0%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Instruction Following70
General70
Math60
Physics60
Reasoning60
Biology60
Chemistry60
Chat50
Code50
Communication50
Tool Calling50
Pricing
Input Price$0.25 / 1M tokens
Output Price$0.75 / 1M tokens
Blended Price (3:1)$0.375 / 1M tokens
Cache Read Price$0.025 / 1M tokens
Speed
Tokens/sec492.8
Time to First Token7.80s
Time to Answer7.80s
Provider Price Ranking
Provider Price Ranking
2 providers
Cheapest: InceptionMost Expensive: NanoGPT
ProviderInputOutput
1InceptionPRIMARY
$0.25
$0.75
2NanoGPT
$0.25
$0.75
Compare pricing across different API providers for this model.