Inception: Mercury 2
inception/mercury-2
118th smartest of 182ReasoningToolsJSON
Intelligence
21.4
118th of 182
Design Elo
1040
3D
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.250
114th cheapest
Context
128K
50K max out
How it compares
Smarter than35%
of all ranked models
Cheaper than66%
of all ranked models
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...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis63th percentile
Intelligence Index
21.4
Coding Index
31.1
GPQA Diamond
77%
Humanity's Last Exam
16%
SciCode
39%
Tau²-Bench (agentic)
71%
Design Arena · Elo1,940 tournaments
3D
1040
svg
1021
Website
1013
Data Viz
1002
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Inception | $0.250 | $0.750 | 128K | 100% |
Specifications
Context window128K
Max output50K
Knowledge cutoff—
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price$0.025/M
ModeratedNo
Mercury 2 FAQ
How much does Mercury 2 cost?
Mercury 2 costs $0.250 per million input tokens and $0.750 per million output tokens via OpenRouter, making it 114th cheapest of 332 paid models.
How smart is Mercury 2?
Mercury 2 scores 21.4 on the Artificial Analysis Intelligence Index, ranking 118th of 182 benchmarked models, with a GPQA Diamond score of 77%.
What is Mercury 2's context window?
Mercury 2 supports a 128K-token context window and can output up to 50K tokens. It accepts text input.