MiniMax M2.1
Fast and lightToolsMiniMax · Released December 2025
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
It is part of MiniMax's M-series, a fast-iterating line focused on conversational quality and long context.
Facts and pricing
- Provider
- MiniMax
- Context window
- 205K tokens
- Input price
- 3.3 credits / 1M tokens ($0.30 raw)
- Output price
- 13.2 credits / 1M tokens ($1.20 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try MiniMax M2.1 now
What MiniMax M2.1 is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
- Long documents: the 205K-token window holds lengthy reports, contracts or papers whole
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a fast and light model like MiniMax M2.1:
- Summarize this article in five bullet points
- Rewrite this email to be shorter and friendlier
- Give me ten name ideas for a hiking newsletter
- Translate this paragraph to Spanish and keep the tone
MiniMax family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| MiniMax M3 | 1.0M | 3.3 | 13.2 | May 2026 |
| MiniMax M2.7 | 205K | 2.6 | 10.6 | March 2026 |
| MiniMax M2.5 | 205K | 1.7 | 9.9 | February 2026 |
| MiniMax M2-her | 66K | 3.3 | 13.2 | January 2026 |
| MiniMax M2.1 | 205K | 3.3 | 13.2 | December 2025 |
| MiniMax M2 | 205K | 2.8 | 11.2 | October 2025 |
| MiniMax M1 | 1M | 4.4 | 24.2 | June 2025 |
| MiniMax-01 | 1.0M | 2.2 | 12.1 | January 2025 |
Frequently asked questions
- What is MiniMax M2.1?
- MiniMax M2.1 is an AI model by MiniMax. MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
- How much does MiniMax M2.1 cost on Zeplik?
- Input tokens cost 3.3 credits per million and output tokens 13.2 credits per million (1 credit = $0.10; the raw provider rates are $0.30 and $1.20 per million). New accounts start with free credits.
- How long can a conversation with MiniMax M2.1 be?
- MiniMax M2.1 has a 205K-token context window (204,800 tokens), which covers the conversation plus any documents you attach.
- Does MiniMax M2.1 support images and tools?
- MiniMax M2.1 is text-only and supports tool calling.
Related models
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...