Mercury 2
inception/mercury-2
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM).
Key facts
- Input price
- $0.25 / 1M tokens
- Output price
- $0.75 / 1M tokens
- Context window
- 128K tokens
- Max output
- 50K tokens
- Accepts
- Text
- Returns
- Text
Example: 1,000 requests with 1,000 input and 500 output tokens each would cost about $0.62 (1M input tokens × $0.25 + 0.5M output tokens × $0.75). Estimate your own usage.
Prices are the provider’s own per-token rates with zero markup, from our price list as of Oct 18, 2026. If a call has extra provider charges (images, audio, web search, cached prompts), you pay the reported cost.
Call it from your code
curl https://api.tokenctr.com/v1/chat/completions \
-H "Authorization: Bearer $TOKENCENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "inception/mercury-2", "messages": [{"role": "user", "content": "Hello!"}]}'Works with any OpenAI-compatible SDK: set the base URL to https://api.tokenctr.com/v1. Quickstart
Benchmarks
Artificial Analysis
- Intelligence index
- 10.8
- Coding index
- 31.1
- Agentic index
- 1.6
Design Arena
| Category | Rank | Elo | Win rate |
|---|---|---|---|
| Models: ASCII art | 70 | 997 | 25.2% |
| Models: SVG | 84 | 996 | 24.6% |
| Models: Data visualization | 112 | 1011 | 22.5% |
| Models: 3D | 113 | 982 | 21.9% |
| Models: UI components | 113 | 996 | 19.6% |
| Models: Code | 118 | 1023 | 21.4% |
| Models: Game dev | 119 | 989 | 19.2% |
| Models: Websites | 120 | 1036 | 22% |
Source: Artificial Analysis indexes and Design Arena results as published in OpenRouter’s model data, fetched Oct 15, 2026. Higher is better. Not measured by TokenCenter. See all rankings.