Inception's diffusion reasoning model for chat, multi-step problem solving, and tool use
6 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
6 providers
Code editing dLLM for autocomplete (FIM) and next-edit suggestions
1 provider
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
7 providers
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...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Mercury 3inception/mercury-3 | Inception |
1M | $0.1 | $0.35 | 2026-10-16 | ||
| Mercury 2.5inception/mercury-2.5 | Inception |
260K | $0.2 | $0.75 | 2026-09-08 | ||
| Mercury Edit 2inception/mercury-edit-2 | Inception |
32K | $0.25 | $0.75 | 2026-03-30 | ||
| Mercury 2inception/mercury-2 | Inception |
128K | $0.25 | $0.75 | 2026-02-24 | ||
| Inception: Mercury 2.5 Previewinception/mercury-2.5-preview | Inception |
260K | $0.04 | $0.15 | — |