AI Agent StoreChina Telecom / TeleAI · Catalog verified
Xing4.0 29B A4B · Free offer
An open-weight text model for coding, document questions and tool-based workflows. This newly listed free service is one way to try it; running your own copy still needs hardware. Independent comparison results are pending.
Catalog added 2026-10-16 UTC · Checked 2026-11-03. This is a newly discovered hosted offer for an already published checkpoint. The exact original release day is not established by the accessible model card.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact catalog ID: xingchen-agi/xing4.0-29b-a4b:free. The model supports tool use and thinking that can be enabled or disabled. It has 29 billion total parameters and activates 4 billion at a time; that does not mean the full weights fit in 4 billion parameters’ worth of memory.
Available thinking settings: off, on. We do not yet have comparable independent results for these settings. The default applied when a request omits effort is unverified.
The publisher provides Apache 2.0 weights and code. The OpenRouter free offer has no stated expiry in today’s catalog; availability can change.
The hosted offer lists 262,144 context tokens and 235,929 maximum output tokens. The downloadable model card describes 256K context, extendable to 512K with a different setup; the extension is not assumed for this hosted offer.
Rates describe the catalog offer observed on 2026-11-03. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Inspect the exact catalog model ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗