AI Agent StoreMeituan · Hosting offer verified
LongCat 2.5 · AI Gateway
Try LongCat 2.5 through an existing Gateway account, with the limits and billing of that hosted offer.
Released 2026-11-02 · First reviewed 2026-11-03 · Checked 2026-11-03.
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 AI Gateway offer ID: meituan/longcat-2.5. Gateway advertises tools, structured output and thinking controls at none, low, medium and high. These are supported controls, not measured quality differences or a verified mapping to native thinking budgets.
The stable hosted offer replaces the preview entry in Gateway’s current catalog. This is a hosting option for the same base model, not another model release.
Gateway declares 1,048,576 combined tokens and a 131,072 output ceiling. Keep these hosted limits separate from the conflicting native output documentation.
Gateway currently lists $0.30 input, $0.006 cached input and $1.20 output per million tokens. Check its quote before budgeting beyond the native provider’s temporary promotion. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Check availability and plans ↗
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 ↗