AI Agent StoreInclusionAI · Hosting offer verified
Ling 3.1 Flash 1019 · AI Gateway
Use Ling 1019 through Gateway, but confirm billing before leaving an application running: its announced free period ends today.
Released 2026-10-30 · First reviewed 2026-10-31 · 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: inclusionai/ling-3.1-flash-1019. Gateway lists text input, tool calls and optional thinking at none, low, medium or high. Check the thinking setting explicitly; the default is not documented. These controls are not measured effort-by-effort results.
A hosted offer for the existing 1019 revision, served by Novita. It is not another base-model release.
Gateway lists 1,000,000 tokens shared by input and output, with a 262,144 output ceiling. If you run the downloadable model yourself, check its separate limits; its card and configuration still disagree.
The free promotion is scheduled to end November 3, 2026. At this review the catalog still returns zero; no extension, exact cutoff timezone or paid rate is verified. This is a transitional quote, not a reliable ongoing cost estimate. 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 ↗