Free, Unlimited DeepSeek Chimera API
On this page
In this tutorial, you will learn how to add DeepSeek Chimera models into your application using Puter.js. You can gain access to TNG Tech's Assembly-of-Experts models such as DeepSeek R1T Chimera, DeepSeek R1T2 Chimera, and TNG R1T Chimera without having to set up the AI server yourself.
Puter.js uses the User-Pays model, where users of your application cover their own AI costs. This means you as a developer don't pay anything for your users' usage, making your app practically free to run. You can scale to unlimited users and pay nothing for the AI or server usage.
Getting Started
Add Puter.js to your project with a single line:
<script src="https://js.puter.com/v2/"></script>
That's it, you're ready to start integrating DeepSeek Chimera into your application.
Example 1: Basic Chat
The DeepSeek R1T2 Chimera is the second generation of the DeepSeek Chimera family, and through the Assembly-of-Experts merge, it is 2x faster than the latest DeepSeek R1 (0528) model.
puter.ai.chat("Explain the concept of quantum computing in simple terms",
{ model: "openrouter:tngtech/deepseek-r1t2-chimera" }
)
.then(response => {
puter.print(response);
});
Full code example:
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain the concept of quantum computing in simple terms",
{ model: "openrouter:tngtech/deepseek-r1t2-chimera" }
)
.then(response => {
puter.print(response);
});
</script>
</body>
</html>
Example 2: Advanced Reasoning
Based on DeepSeek R1, the Chimera variant also excels at reasoning tasks.
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
async function streamResponse() {
const response = await puter.ai.chat(
"A farmer needs to cross a river with a wolf, a goat, and a cabbage. The boat can only carry the farmer and one item. If left alone, the wolf will eat the goat, and the goat will eat the cabbage. How can the farmer get everything across safely?",
{ model: "openrouter:tngtech/deepseek-r1t2-chimera", stream: true }
);
for await (const part of response) {
if(part?.reasoning)
puter.print(part?.reasoning);
else
puter.print(part?.text);
}
}
streamResponse();
</script>
</body>
</html>
Example 3: Creative Storytelling
The TNG R1T Chimera is TNG Tech's experimental LLM, based on the DeepSeek R1T Chimera. It excels at creative storytelling and character interaction.
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
async function streamResponse() {
const response = await puter.ai.chat(
"Write a short story about an old lighthouse keeper who discovers something mysterious washed ashore during a storm",
{ model: "openrouter:tngtech/tng-r1t-chimera", stream: true }
);
for await (const part of response) {
if(part?.reasoning)
puter.print(part?.reasoning);
else
puter.print(part?.text);
}
}
streamResponse();
</script>
</body>
</html>
List of DeepSeek Chimera models
You can use the following DeepSeek Chimera model variants with Puter.js:
openrouter:tngtech/tng-r1t-chimera:free
openrouter:tngtech/tng-r1t-chimera
openrouter:tngtech/deepseek-r1t2-chimera:free
openrouter:tngtech/deepseek-r1t2-chimera
openrouter:tngtech/deepseek-r1t-chimera:free
openrouter:tngtech/deepseek-r1t-chimera
Conclusion
Using Puter.js, you can gain access to DeepSeek Chimera models without having to set up the AI server yourself. And thanks to the User-Pays model, your users cover their own AI usage, not you as the developer. This means you can build powerful applications without worrying about AI usage costs.
You can find all AI features supported by Puter.js in the documentation.
Related
Free, Serverless AI and Cloud
Start creating powerful web applications with Puter.js in seconds!
Get Started Now