Inception: Mercury 2
inception/mercury-2
Try Mercury 2 for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// 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>
Model Card
Mercury 2 is a diffusion-based reasoning language model from Inception Labs that refines all tokens in parallel rather than generating them sequentially, achieving over 1,000 tokens per second — roughly 5x faster than speed-optimized competitors like Claude Haiku and GPT-5 Mini at comparable quality.
On reasoning benchmarks, Mercury 2 scores 91.1 on AIME 2025 and 73.6 on GPQA. It also placed second on the Copilot Arena leaderboard for quality while ranking first for speed overall.
With a 128K context window, it is purpose-built for latency-sensitive applications — real-time assistants, high-throughput pipelines, and cost-conscious production workloads where reasoning capability matters.
Context Window 128K
tokens
Max Output 128K
tokens
Input Cost $0.25
per million tokens
Output Cost $0.75
per million tokens
Release Date Mar 4, 2026
Try Mercury 2 for free
Try Mercury 2 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Mercury 2 performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 77.0% |
| Humanity's Last Exam Cross-domain reasoning | 17.1% |
| SciCode Scientific programming | 37.7% |
| IFBench Instruction following | 69.8% |
| LCR Long-context reasoning | 43.7% |
| Terminal-Bench Hard Agentic terminal tasks | 26.5% |
| τ²-Bench Tool use / agents | 70.8% |
Scores sourced from Artificial Analysis.
Frequently Asked Questions
You can access Mercury 2 by Inception through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Mercury 2 is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Mercury 2 is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.25 |
| Output | $0.75 |
Mercury 2 was created by Inception and released on Mar 4, 2026.
Mercury 2 supports a context window of 128K tokens. For reference, that is roughly equivalent to 256 pages of text.
Mercury 2 can generate up to 128K tokens in a single response.
Mercury 2 scores 10.8 on the Artificial Analysis Intelligence Index, outperforming 43% of tracked models. On coding, it scores 31.1 (outperforms 37% of models).
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.
Add Mercury 2 to your app for free
Developers can integrate Mercury 2 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.