AI Agent StoreMiniMax · Free offer no longer listed
MiniMax M3.1 Flash · OpenRouter free
This free OpenRouter offer is no longer listed. The stable model is available through a separate paid offer.
Released 2026-10-19 · Catalog added 2026-10-19 UTC · Checked 2026-11-03. Catalog addition and provider launch are separate dates.
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.
Previously documented features
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: minimax/minimax-m3.1-flash:free. Before removal, OpenRouter listed text, image and video input, tools, and always-on thinking. These are historical features of the removed offer.
Available thinking settings: low, medium, high, xhigh, max. We do not yet have comparable independent results for these settings. The documented OpenRouter default is max when effort is omitted. A default is not a recommendation for every task.
The free OpenRouter ID is absent on October 23. Gateway’s MiniMax-served promotion separately ended October 22; do not assume either service is still free.
The former free offer listed 1,000,000 context tokens and 524,288 maximum output tokens. No current capacity is verified for this removed ID.
The former zero-price quote is historical. Current access and prices for this exact free ID are not verified. 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 a current alternative
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 ↗