Inception
Mercury 2
A diffusion-based reasoning LLM that generates text via parallel refinement (not token-by-token), delivering real-time latency with ~1k tokens/sec plus 128K context and built-in tool/JSON support.
Inception model updatesModel Snapshot
TypeLanguage
ReleaseFeb 24, 2026
Context128,000
Tagstool-use, reasoning
Overall
Rank #126 across 526
32.8
Coding
Rank #127 across 436
30.6
Blended Price
Rank #118 across 357
$0.375/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed758.7 tok/s
First Token2.83s
Max Output128,000
Pricing
Blended$0.375/M
Input$0.250/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 32.8 | #126 |
| Artificial Analysis Coding Index | coding | 30.6 | #127 |
| GPQA | reasoning | 77.0% | #148 |
| Humanity's Last Exam | reasoning | 15.5% | #105 |
| SciCode |