Model specification · Inception

Mercury 2

inception/mercury-2

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...

SpecificationsReported values
Context window
128K
Maximum output
50K
Architecture
text->text
Tokenizer
Other
Knowledge cutoff
Moderated
No
Input modalities
text
Output modalities
text
Full pricingUSD where reported
PriceStandard
Input$0.250 / M
Output$0.750 / M
Benchmark indexesReported indexes
Intelligence
21.4
Coding
31.1
Agentic
9.6
Design Arena Elo
1020
Example workload costsStandard pricing only
WorkloadInput / outputCache shareEstimated cost
Quick check10K / 1K × 10%$0.00325
Long analysis100K / 4K × 150%$0.017
Workday20K / 2K × 1,00030%$5.15