All Models
Mercury 2
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
Available Providers (6)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Vercel AI Gateway | inception/mercury-2 | $0.25/MTok | $0.75/MTok | 128K | 128K | |
 Inception | mercury-2 | $0.25/MTok | $0.75/MTok | 128K | 50K | |
 Kilo Gateway | inception/mercury-2 | $0.25/MTok | $0.75/MTok | 128K | 50K | |
 OpenRouter | inception/mercury-2 | $0.25/MTok | $0.75/MTok | 128K | 50K | |
 NanoGPT | mercury-2 | $0.25/MTok | $0.75/MTok | 128K | 50K | |
 Venice AI | mercury-2 | $0.31/MTok | $0.94/MTok | 128K | 50K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output