AI Agent StoreInclusionAI · Hosted route documented
Ling 3.1 Flash
Hybrid reasoning model with a temporary Vercel AI Gateway promotion through October 13, 2026. The standard route begins billing afterward; the -free route stops serving. Exact cutoff time and later rates are unverified. No independent matched score is assigned.
Provider documentation discovered 2026-10-02 · Checked 2026-10-11. The provider launch date is unverified; discovery is a separate date.
We still need comparable independent tests. You can compare the confirmed prices and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating, or recommend a thinking setting. Try it on your own tasks before switching. Results for an older or differently configured version may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity, often called the context window, is the amount it can handle in a request. A dash means we could not confirm the price.
Exact AI Gateway route ID: inclusionai/ling-3.1-flash. Vercel documents text input, tool use, hybrid reasoning and a 32,768-token output cap including reasoning. Its exact Gateway catalog lists a reasoning toggle plus none/low/medium/high effort controls; a native mapping and default are unverified, and no matched independent effort sweep is available. Test accuracy, speed and reliability on your own tasks.
Thinking settings listed by AI Gateway: none, low, medium, high. These controls apply to this AI Gateway service. We have not confirmed how they match the model maker’s settings, which is the default, or how they perform in comparable independent tests. Verify the exact Gateway catalog entry ↗
The alternate inclusionai/ling-3.1-flash-free route stops serving at promotion expiry instead of beginning paid billing. This promotion is specific to AI Gateway; it does not establish a free direct-provider API.
AI Gateway’s exact models API declares a 262,144-token hosted context and 32,768-token output allowance; the model webpage rounds context to 262K. Gateway availability was announced September 30, separately from the unverified base-model launch date.
Newly listed OpenRouter offer. Zero input/output are the observed routed quote; duration, capacity and native API defaults are unverified. This offer is separate from the Gateway promotion. Inspect the separate OpenRouter offer ↗
The cited Gateway promotion currently has free input and output. Post-promotion prices and exact expiry time are unverified; no permanent zero rate or routed OpenRouter offer is inferred. Your bill can also depend on discounts for reused input, which provider handles the request, speed options, tools, retries and charged thinking tokens.
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, token use and total cost. Even at the same price per token, a different version can cost more if it uses more tokens.
Compare caching and long-context costs ↗