AI Agent StoreMeituan · Native API verified
LongCat 2.5
Use text and pictures in coding and multi-step agent work. Check the limits of your chosen service before sending a large project.
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 provider API ID: LongCat-2.5. Thinking can be enabled or disabled. The parameter guide permits a thinking budget up to 262,144 tokens but does not establish an omitted default. Temperature is fixed by thinking mode; other supplied values are overridden. No matched independent effort or speed comparison is available here.
Create an API key and fund the account. The API changelog dates availability November 2; the announcement is dated November 1. Compatible chat and agent interfaces are documented. Public downloadable 2.5 weights are not verified.
The native API shares 1,048,576 tokens between input and output. Its parameter reference allows 262,144 output tokens, while the quick-start guide still says 128K. Confirm the usable output ceiling before relying on a long answer.
Limited-time native rates are $0.30 input, $0.006 cached input and $1.20 output per million tokens. The promotion has no verified end date. The platform bill is authoritative; failed requests are not billed. The pricing page’s 500K-output worked example is not a supported output limit. 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 ↗
More setup and licensing details ↗
More setup and licensing details ↗
More setup and licensing details ↗
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 ↗