Inception/ Mercury
Mercury 2
inception/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...
Released
2026-03-04
Context window
128K
Max output
50K
Weights
Closed
Modalities
Input
Text
Output
Text
Identity
- Version
- mercury-2
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | inception/mercury-2 | openai_chat | 128K | 50K | Text | Text | ReasoningTool callStructuredTemperature | Default reasoning: medium | input $0.25/M · cache read $0.025/M output $0.75/M | Yes |
| Inception | mercury-2 | openai_chat | 128K | 50K | Text | Text | ReasoningTool callStructuredTemperature | - | input $0.25/M · cache read $0.025/M output $0.75/M | Yes |
| Kilo Gateway | inception/mercury-2 | openai_chat | 128K | 50K | Text | Text | ReasoningTool callStructuredTemperature | - | input $0.25/M · cache read $0.025/M output $0.75/M | Yes |
| Vercel AI Gateway | inception/mercury-2 | openai_chat | 128K | 50K | Text | Text | ReasoningTool callStructuredTemperature | - | input $0.25/M · cache read $0.025/M output $0.75/M | Yes |
Capabilities
ReasoningTool callStructuredTemperature