Inception
Inception: Mercury 2.5
inception/mercury-2.5
12,3
Quality Index
857t/s
Output Speed
$0.75
Preis Output / 1M
text
Specs
| Quality Index Artificial Analysis Intelligence Index | 12,3 / 100 |
|---|---|
| Output Speed Tokens pro Sekunde | 856,6 t/s |
| Latenz (TTFT) Time-to-First-Token | 3,46 s |
| Preis Input USD je 1 Mio. Input-Tokens | $0.25 / 1M |
| Preis Output USD je 1 Mio. Output-Tokens | $0.75 / 1M |
| Context Window Maximale Tokens pro Anfrage | — |
| Release Veröffentlichungsdatum | Sep 2026 |
Über Inception: Mercury 2.5
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Direkte Vergleiche
Wie schlägt sich Inception: Mercury 2.5 gegen die Top-Konkurrenz?