MiniMax-M3.1-Flash
Overview
MiniMax-M3.1-Flash, also known as Space Bunny, is a MiniMax M-series model designed for workplace automation, software engineering, visual reasoning, and professional analysis. It combines multi-step task execution with frontend and presentation creation, supporting workflows that turn information and visual references into practical deliverables.
Model ID: minimax-m3.1-flash
Key Features
- Workplace Automation: Designed for complex, multi-step workflows. MiniMax reports a score of 72.5% on AutomationBench-AA.
- Software Engineering: Supports understanding codebases, fixing bugs, and building features. MiniMax reports 73.67% on DeepSWE.
- Visual Reasoning: Handles visual understanding and chart reasoning. MiniMax reports 91.0 on BabyVision with tools and 82.5 on CharXiv RQ.
- Frontend and Presentation Creation: Supports producing frontend implementations and presentations in tool-enabled workflows.
- Knowledge and Reasoning: Covers everyday questions, professional analysis, and scientific reasoning, with MiniMax-reported results of 56% on AA-Omniscience, 48% on HLE, and 22.3% on CritPt.
- Tool-Based Analysis: MiniMax reports 76.15 on BankerToolBench in its internal comparison.
Best Use Cases
- Multi-Step Office Work: Coordinate information gathering, analysis, and deliverable preparation across a connected workflow.
- Codebase Maintenance: Investigate bugs, understand existing implementations, and develop features within real software projects.
- Visual Analysis and Prototyping: Interpret charts and visual references, then use the findings to guide frontend development.
- Research and Presentations: Organize knowledge, analyze technical or business questions, and turn findings into presentation content.
Capabilities and Limitations
| Capability | Description |
|---|---|
| Reasoning | Supports reasoning tasks; available thinking modes and effort controls are not confirmed for this release. |
| Multimodal | Supports visual understanding; the exact supported input and output modalities are not confirmed for this release. |
| Context Window | 1M tokens. |
| Max Output | 512K tokens. |
| Tool Use | Tool-assisted workflows are reported; API function-calling support and controls are not confirmed for this release. |
Known Limitations
- Workflow automation and frontend or presentation creation require an environment with the appropriate tools, data access, and execution permissions.
Standard Pricing
The token prices below are shown in USD per 1 million tokens.
| Model | Input (USD / 1M Tokens) | Cache Write (USD / 1M Tokens) | Cache Read (USD / 1M Tokens) | Output (USD / 1M Tokens) | Web Search (USD / use) |
|---|---|---|---|---|---|
| MiniMax-M3.1-Flash | $0.15 | $0.15 | $0.015 | $0.60 | - |
Credits settlement: B.AI converts charges at 1 USD = 1,000,000 Credits and deducts Credits from the account balance.
Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.