MiniMax M3.1 Flash
October 19 hosted reasoning model available through MiniMax API, M Plan and MiniMax Code. Downloadable weights remain upcoming.
- Practical guide
Access choices, version boundaries and evaluation limits.
- Official model source
Verify the exact checkpoint or provider contract.
- Official model source
Verify the exact checkpoint or provider contract.
Model Specificationsminimax
Hosted MiniMax API; M Plan and MiniMax Code are distinct access products.
USD per 1M tokens: $0.15 input, $0.60 output, $0.015 cached input. Plan entitlements are separate.
Scoped Terms🚀Function Overview
Primary-source contract checked October 21, 2026. No independent model request or hardware test was executed.
Key Features
- Official API ID: MiniMax-M3.1-Flash; reasoning is always on.
- Text, image and video input with text output; 1M context as documented by the integration guide.
- Input $0.15 / output $0.60 / cached input $0.015 per 1M tokens at the October 19 launch.
- Weights are announced for later release; do not infer a downloadable license or free local access.
- Publisher throughput and benchmark figures are configuration-specific, not independently executed here.
Use Cases
- •Compare the exact checkpoint and provider contract
- •Evaluate a permitted task with a verifiable reference
⚙️Input Parameters
model
stringMiniMax-M3.1-Flash — follow the selected official runtime or provider interface; this is not a universal hosted alias.
task_input
provider-specificUse the documented input schema; see official sources for supported modalities and request fields.
Quick Actions
Technical Specifications
- Hardware Type
- Hosted MiniMax API; M Plan and MiniMax Code are distinct access products.
- Commercial Use
- Hosted commercial service under provider terms; no released-weight license is established.
- Pricing
- USD per 1M tokens: $0.15 input, $0.60 output, $0.015 cached input. Plan entitlements are separate.