Reflection AI: Beam 1.0
reflection/beam-1.0-501b-a23b
Try Beam 1.0 for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "reflection/beam-1.0-501b-a23b"
}).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: "reflection/beam-1.0-501b-a23b"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Beam 1.0 is an open-weight model from Reflection AI. It is a sparse mixture-of-experts model with 501B total parameters and 23B active per token, released under the Apache 2.0 license.
Reflection positions it for software engineering, multi-step tool use, and math and science reasoning. It supports configurable reasoning effort, function calling, and structured outputs. On Reflection's own launch numbers it scores 80.9 on SWE-bench Verified and 80.1 on Terminal-Bench v2.1, roughly level with GLM 5.2 (81.0) on Terminal-Bench and behind Kimi K3 (88.3). These figures are vendor-reported and had not been independently verified at launch.
It accepts text input and returns text, with a context window of about 1M tokens. It suits developers building coding agents and tool-calling workflows through an API.
Context Window 1M
tokens
Max Output 944K
tokens
Input Cost $1
per million tokens
Output Cost $3
per million tokens
Input text
modalities
Tool Use Yes
Release Date Oct 16, 2026
Try Beam 1.0 for free
Try Beam 1.0 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Beam 1.0 by Reflection AI 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.
Beam 1.0 is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Beam 1.0 is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $1 |
| Output | $3 |
Beam 1.0 was created by Reflection AI and released on Oct 16, 2026.
Beam 1.0 supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,097 pages of text.
Beam 1.0 can generate up to 944K tokens in a single response.
Beam 1.0 accepts the following input types: text. It produces: text.
Yes, Beam 1.0 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Beam 1.0 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.
Add Beam 1.0 to your app for free
Developers can integrate Beam 1.0 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.