ricursiveai: Ripple 65B Preview
ricursiveai/ripple-65b-preview
Try Ripple 65B Preview 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: "ricursiveai/ripple-65b-preview"
}).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: "ricursiveai/ripple-65b-preview"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Ripple 65B Preview is an open-weight dense Transformer language model from Ricursive Intelligence, released under the Apache 2.0 license. It has 65B parameters, was pretrained on 12T tokens, and supports a 1M-token context window with native tool calling.
Post-training was relatively light, with a focus on agentic coding and reasoning. Ricursive's model card reports 80.5% on Terminal-Bench 2.1 (self-reported), 76.5% on SWE-bench Verified, 61.42% on SWE-bench Pro v1.0, and 98.3% on AIME 2025. In the card's comparison table, its Terminal-Bench 2.1 score is above Nemotron 3 Ultra 550B (56.4%) and Muse Spark Open 816B (76.4%), though evaluation harnesses differ across rows.
It suits developers building coding agents and tool-calling workflows that need a long context window at a low per-token price.
Context Window 1M
tokens
Max Output 131K
tokens
Input Cost $0.2
per million tokens
Output Cost $0.6
per million tokens
Input text
modalities
Tool Use Yes
Release Date Nov 4, 2026
Try Ripple 65B Preview for free
Try Ripple 65B Preview instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Ripple 65B Preview by ricursiveai 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.
Ripple 65B Preview 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.
Ripple 65B Preview 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 | $0.2 |
| Output | $0.6 |
Ripple 65B Preview was created by ricursiveai and released on Nov 4, 2026.
Ripple 65B Preview supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,097 pages of text.
Ripple 65B Preview can generate up to 131K tokens in a single response.
Ripple 65B Preview accepts the following input types: text. It produces: text.
Yes, Ripple 65B Preview supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Ripple 65B Preview 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 Ripple 65B Preview to your app for free
Developers can integrate Ripple 65B Preview for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.