Thinking Machines Lab: Inkling FP4
thinkingmachines/inkling
Access Inkling FP4 from Thinking Machines Lab using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "thinkingmachines/inkling"
}).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", {
model: "thinkingmachines/inkling"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="thinkingmachines/inkling",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "thinkingmachines/inkling",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
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.
Context Window 524K
tokens
Max Output 524K
tokens
Input Cost $1
per million tokens
Output Cost $4.05
per million tokens
Release Date Jul 15, 2026
Model Playground
Try Inkling FP4 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Inkling FP4 by Thinking Machines Lab through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Inkling FP4 to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $1 |
| Output | $4.05 |
Inkling FP4 was created by Thinking Machines Lab and released on Jul 15, 2026.
Inkling FP4 supports a context window of 524K tokens. For reference, that is roughly equivalent to 1,049 pages of text.
Inkling FP4 can generate up to 524K tokens in a single response.
Yes — the Inkling FP4 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 Inkling FP4 to your app without worrying about API keys or setup.
Read the Docs View Tutorials