Inception
Mercury 2.5
Mercury 2.5 is Inception’s diffusion-based reasoning model for chat, agents, and structured workflows, with tool calling, structured outputs, and a 260K context window.
Inception model updatesModel Snapshot
TypeLanguage
ReleaseSep 8, 2026
Context260,000
Tagsimplicit-caching, reasoning, tool-use, structured-output
Overall
Rank #357 across 699
12.3
Coding
No rank
n/a
Blended Price
Rank #112 across 425
$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 Speed856.6 tok/s
First Token3.46s
Max Output65,536
Pricing
Blended$0.375/M
Input$0.250/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 12.3 | #357 |
| Humanity's Last Exam | reasoning | 11.8% | #275 |
| SciCode | coding, reasoning | 38.5% | #160 |
| Output Speed | speed | 856.6 tok/s | #2 |
| Time to First Token |