Thinking Machines Lab API
Access Thinking Machines Lab instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain AI like I'm five!", {
model: "thinkingmachines/inkling"
}).then(response => {
console.log(response);
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain AI like I'm five!", {
model: "thinkingmachines/inkling"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of Thinking Machines Lab Models
Inkling Small
thinkingmachines/inkling-small
Inkling Small is a mixture-of-experts model from Thinking Machines Lab, the AI research company co-founded by former OpenAI CTO Mira Murati. Released on July 30, 2026, about two weeks after the flagship Inkling FP4, it has 276 billion total parameters with 12 billion active per token, roughly a quarter of Inkling FP4's active-parameter count, and its weights are released under an Apache 2.0 license. Like its larger sibling, the model is multimodal, accepting text, image, and audio inputs and producing text output, and it supports controllable reasoning effort. Thinking Machines Lab reports 80.2% on SWE-bench Verified, 89.5% on GPQA Diamond, and 82.2% on IFBench. On the third-party Artificial Analysis Intelligence Index it scores 40, within a point of Inkling FP4's 41, and the company says it beats Inkling FP4 on several reasoning and coding benchmarks while trailing it on factual-knowledge evaluations. It is available through Together AI's inference platform.
ChatInkling FP4
thinkingmachines/inkling
Inkling FP4 is a mixture-of-experts model from Thinking Machines Lab, the AI research company co-founded by former OpenAI CTO Mira Murati. It was released in July 2026 as Thinking Machines Lab's first open-weights model, with 975 billion total parameters and 41 billion active per token, and is served here in FP4 precision. The model is multimodal, accepting text, image, and audio inputs and producing text output. It supports controllable reasoning effort, letting a request trade latency and cost for more chain-of-thought before answering. At its highest reasoning effort, Thinking Machines Lab reports 97.1% on AIME 2026, 87.2% on GPQA Diamond, and 77.6% on SWE-bench Verified. It launched on Together AI's inference platform the same day as the model's release.
Frequently Asked Questions
The Thinking Machines Lab API gives you access to models for AI chat. Through Puter.js, you can start using Thinking Machines Lab models instantly with zero setup or configuration.
Puter.js supports a variety of Thinking Machines Lab models, including Inkling Small and Inkling FP4. Find all AI models supported by Puter.js in the AI model list.
With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.
Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.
Yes — the Thinking Machines Lab API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.