Inception: Mercury 3
This model is no longer available.Add AI to your application with Puter.js.
Explore Other ModelsModel Card
Mercury 3 is a diffusion language model from Inception Labs. It generates and refines tokens in parallel instead of one at a time, and it is the largest Mercury model so far, with over 40 times the parameters of Mercury 1.
Inception reports 1,068 tokens per second on NVIDIA GPUs and says it matches or beats GPT-6 Luna and Claude Haiku 5.5 across a range of benchmarks. It also reports that Mercury 3 completed 50% of 50 live Mind2Web browser tasks, more than GPT-6.1-Sol. These figures are Inception's own and were not independently verified.
The context window is 1M tokens, up from 260K in Mercury 2.5, with up to 131,072 output tokens through OpenRouter. It supports tool calling and an OpenAI-compatible API. Inception lists browser agents, real-time search, tutoring, and customer support as target uses, so it fits latency-sensitive applications.
Context Window 1M
tokens
Max Output 131K
tokens
Input Cost $0.1
per million tokens
Output Cost $0.35
per million tokens
Input text
modalities
Tool Use Yes
Release Date Oct 19, 2026
Code Example
Add AI to your app with the Puter.js AI API, no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").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").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From Inception
Frequently Asked Questions
Mercury 3 is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.1 |
| Output | $0.35 |
Mercury 3 was created by Inception and released on Oct 19, 2026.
Mercury 3 supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,000 pages of text.
Mercury 3 can generate up to 131K tokens in a single response.
Mercury 3 accepts the following input types: text. It produces: text.
Yes, Mercury 3 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Mercury 3 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 AI to your application without worrying about API keys or setup.
Explore Models View Tutorials