XingChen: Xing4.0 29B A4B
Try Xing4.0 29B A4B 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: "xingchen-agi/xing4.0-29b-a4b"
}).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: "xingchen-agi/xing4.0-29b-a4b"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Xing4.0 29B A4B is an open-weight mixture-of-experts language model from China Telecom Artificial Intelligence Technology Co., Ltd. (TeleAI), published under the XingChen-AGI organization. It is part of the Xing series, formerly TeleChat, and is released under the Apache 2.0 license.
The model has 29B total parameters with 4B active per token, and a 256K context window. It is aimed at agent-style work such as multi-step planning and tool calling, and supports function calling with structured JSON output.
On the benchmarks published on its Hugging Face model card, it scores 75.0 on SWE-bench Verified, 57.5 on Terminal-Bench 2.1, and 90.0 on AIME2026. The card lists Gemma4-26B-A4B at 30.0 on Terminal-Bench 2.1 and Qwen3.6-35B-A3B at 51.5, while Qwen3.6 is ahead on SWE-bench Verified (76.0) and AIME2026 (92.7). These figures are vendor-reported. It suits developers building coding and tool-calling agents through an API.
Context Window 262K
tokens
Max Output 262K
tokens
Input Cost $0.22
per million tokens
Output Cost $0.9
per million tokens
Input text
modalities
Tool Use Yes
Release Date Sep 18, 2026
Try Xing4.0 29B A4B for free
Try Xing4.0 29B A4B instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Xing4.0 29B A4B by XingChen 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.
Xing4.0 29B A4B 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.
Xing4.0 29B A4B 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 | $0.22 |
| Output | $0.9 |
Xing4.0 29B A4B was created by XingChen and released on Sep 18, 2026.
Xing4.0 29B A4B supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Xing4.0 29B A4B can generate up to 262K tokens in a single response.
Xing4.0 29B A4B accepts the following input types: text. It produces: text.
Yes, Xing4.0 29B A4B supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Xing4.0 29B A4B 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 Xing4.0 29B A4B to your app for free
Developers can integrate Xing4.0 29B A4B for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.