# Mercury 2

> Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).

**ID**: `inception/mercury-2`  
**Creator**: inception  
**Category**: text  
**Context**: 128K tokens  
**Pricing**: $0.18 / $0.54 per 1M · billed by your provider (BYOK)  
**Released**: 2026-03-04  
**Web page**: https://anyrouter.dev/model/inception/mercury-2

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, reasoning, streaming, function-calling

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "inception/mercury-2",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| fluence-byok | $0.18/M (list) | $0.54/M (list) |
| inception-byok | $0.18/M (list) | $0.54/M (list) |
| nano-gpt-byok | $0.18/M (list) | $0.54/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Source

- Upstream docs: https://openrouter.ai/inception/mercury-2