Arcee AI: Maestro Reasoning API

Access Arcee AI: Maestro Reasoning from Arcee AI using Puter.js AI API.

Get Started

Model Card

Arcee Maestro Reasoning is a 32B parameter flagship analysis model derived from Qwen 2.5-32B, tuned with DPO and chain-of-thought reinforcement learning for step-by-step logical reasoning. It features a 128k context window and doubles pass-rates on MATH and GSM-8K benchmarks compared to its 7B predecessor. The model is designed for complex problem-solving, abstract reasoning, and scenario modeling with transparent reasoning traces suited for audit-focused industries.

Context Window

N/A

tokens

Max Output

32,000

tokens

Input Cost

$0.9

per million tokens

Output Cost

$3.3

per million tokens

API Usage Example

Add Arcee AI: Maestro Reasoning 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: "arcee-ai/maestro-reasoning"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

Get started with Puter.js

Add Arcee AI: Maestro Reasoning to your app without worrying about API keys or setup.

Read the Docs View Tutorials