inception/mercury
Model Card
Mercury is the world's first commercial diffusion large language model (dLLM) from Inception Labs that generates text 5-10x faster than traditional autoregressive LLMs by predicting multiple tokens in parallel. It's designed for latency-sensitive applications like voice agents, search interfaces, and chatbots while matching the quality of speed-optimized models like Claude 3.5 Haiku.
Context Window
N/A
tokens
Max Output
16,384
tokens
Input Cost
$0.25
per million tokens
Output Cost
$1
per million tokens
API Usage Example
Add Inception: Mercury to your app with just a few lines of code.
No API keys, no backend, no configuration required.
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "inception/mercury"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Get started with Puter.js
Add Inception: Mercury to your app without worrying about API keys or setup.
Read the Docs View Tutorials