Mercury 2.5
Mercury 2.5 is a diffusion-based language model developed by Inception. It utilizes parallel token generation to prioritize reasoning capabilities and fast performance for text-based tasks.
Mercury 2.5 specs and pricing
- Provider: Inception
- Released: September 8, 2026
- Context window: 260K tokens
- Max output: 66K tokens
- Input: text
- Output: text
- Price: $0.04 input / $0.15 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Mercury 2.5 is good at
- Complex logic and reasoning tasks
- High-speed text generation
- Applications requiring integrated tool calling
To-dos to try with Mercury 2.5
- Analyze a complex technical document and outline the logical steps required to solve a specific problem.
- Use tool calling to fetch live data and synthesize it into a structured report.
- Draft a multi-step project plan that requires reasoning through dependencies and deadlines.
FAQ
- What is a diffusion LLM? Mercury 2.5 is a diffusion LLM, meaning it generates and refines multiple tokens in parallel rather than producing them sequentially.
- What types of input does Mercury 2.5 support? This model is designed to process and generate text-based input and output.
- How much does Mercury 2.5 cost? Mercury 2.5 costs $0.04 per million input tokens and $0.15 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.13 credits ($1 = 100 credits).
- What is the context window of Mercury 2.5? Mercury 2.5 can read up to 260K tokens at once and write up to 66K tokens in one reply.
- Can I use Mercury 2.5 without coding? Yes. In todo.is you pick Mercury 2.5 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.