Mercury 2 API

Access Mercury 2 from Inception using Puter.js AI API.

Get Started

Model Card

Mercury 2 is a diffusion-based reasoning language model by Inception Labs that generates text by refining multiple tokens in parallel rather than sequentially, achieving speeds of ~1,000 tokens per second — roughly 5-10x faster than comparable models like Claude Haiku and GPT-5 Mini. It scores competitively on reasoning benchmarks (91.1 AIME 2025, 73.6 GPQA) while offering pricing at $0.25/$0.75 per million input/output tokens with a 128K context window. It targets latency-sensitive production workloads like agent loops, voice assistants, coding tools, and real-time search.

Context Window N/A

tokens

Max Output 50K

tokens

Input Cost $0.25

per million tokens

Output Cost $0.75

per million tokens

Release Date Mar 4, 2026

 

API Usage Example

Add Mercury 2 to your app with just a few lines of code.
No API keys, no backend, no configuration required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "inception/mercury-2"
}).then(response => {
    document.body.innerHTML = response.message.content;
});

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "inception/mercury-2"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

More Models from Inception

Chat

Mercury Coder

Mercury Coder is a diffusion-based large language model specialized for code generation that achieve...

 Chat

Mercury

Mercury is the world's first commercial diffusion large language model (dLLM) from Inception Labs th...

View all Inception models →

Frequently Asked Questions

What is this Mercury 2 API about?

The Mercury 2 API gives you access to Inception's chat model through Puter.js. With just a few lines of JavaScript, you can integrate Mercury 2 into any web app or Node.js project — no API keys, no backend, and no configuration required.

Who created Mercury 2?

Mercury 2 was created by Inception and released on Mar 4, 2026.

What is the max output length of Mercury 2?

Mercury 2 can generate up to 50K tokens in a single response.

How much does it cost?
The Mercury 2 API is available through the User-Pays Model. As a developer, you can add the Mercury 2 API to your app for free — your users pay for their own AI costs directly.
Price per 1M tokens
Input$0.25
Output$0.75
How do I access the Mercury 2 API?

You can access the Mercury 2 API with just a few lines of JavaScript — no API keys, no backend, and no configuration required. Include the Puter.js library in your project and start making calls right away. For more details, check out our documentation.

Does the Mercury 2 API work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Mercury 2 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Mercury 2 to your app without worrying about API keys or setup.

Read the Docs View Tutorials