MiniMax · Provider documented

MiniMax M3.1 Flash Preview

The earlier M Plan and MiniMax Code preview. The stable M3.1 Flash release has its own page; do not use this preview’s identity for new tests.

First reviewed 2026-10-01 · Checked 2026-11-03. A provider launch date and public per-token prices are not verified.

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.

Input / 1M tokens—Provider specifications · prices unverified

Output / 1M tokens—Provider specifications · prices unverified

Documented capacity1.00MSee input limits below

Cached input / 1M—Provider specifications · prices unverified

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: MiniMax-M3.1-Flash-Preview. Provider documentation declares text, image, video input and tool-calling support.

Available thinking settings: low, medium, high, xhigh, max. We do not yet have comparable independent results for these settings. The documented API default is max when effort is omitted. A default is not a recommendation for every task.

MiniMax’s current API documentation now names MiniMax-M3.1-Flash. This historical preview page retains the previously documented settings; the preview ID’s present behavior is not verified.

A provider maximum output allowance is not verified. The 4,096-token request in the Anthropic documentation is an example, not a published model limit; thinking and answer tokens share the request budget.

This model is absent from the reviewed routed catalog. Subscription access does not establish a public per-token API rate. 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 ↗

Provider documentation ↗

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 ↗