TNG: DeepSeek R1T2 Chimera API

Access TNG: DeepSeek R1T2 Chimera from TNG Technology using Puter.js AI API.

Get Started

Model Card

DeepSeek R1T2 Chimera is TNG Tech's second-generation 671B parameter tri-parent model assembled from DeepSeek R1-0528, R1, and V3-0324. It runs ~20% faster than R1 and 2x faster than R1-0528 while scoring higher on benchmarks like GPQA and AIME-24, with improved think-token consistency.

Context Window

N/A

tokens

Max Output

163,840

tokens

Input Cost

$0.25

per million tokens

Output Cost

$0.85

per million tokens

API Usage Example

Add TNG: DeepSeek R1T2 Chimera 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: "tngtech/deepseek-r1t2-chimera"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

Get started with Puter.js

Add TNG: DeepSeek R1T2 Chimera to your app without worrying about API keys or setup.

Read the Docs View Tutorials