Xing4.0 29B A4B: pricing, context and benchmarks

What you need to know about Xing4.0 29B A4B

Xingchen AGI, based in China, put Xing4.0 29B A4B online on October 16, 2026. It accepts text as input and produces text. Its context window reaches 262,144 tokens, larger than 58 % of the models in the registry, and it can write up to 235,929 tokens in one go.

It is a recent model: real-world feedback and independent scores are still scarce.

Xing4.0 29B A4B pricing

Xing4.0 29B A4B is free on OpenRouter. Free variants usually have strict rate limits and can be withdrawn without notice: keep a paid fallback model for regular use.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for Xing4.0 29B A4B. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It can answer in an enforced JSON format (structured outputs).
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.

Its weights are open and downloadable from Hugging Face (apache-2.0 licence): you can run it on your own machines without sending your data to a third party. With 31,215,031,088 billion parameters, it needs about 17,442,757,872 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 11,556 times on Hugging Face last month.