How much does MiniMax-01 cost on Zeplik?

Input tokens cost 2.2 credits per million and output tokens 12.1 credits per million (1 credit = $0.10; the raw provider rates are $0.20 and $1.10 per million). New accounts start with free credits.

How long can a conversation with MiniMax-01 be?

MiniMax-01 has a 1.0M-token context window (1,000,192 tokens), which covers the conversation plus any documents you attach.

Does MiniMax-01 support images and tools?

MiniMax-01 accepts image input and does not support tool calling.

MiniMax-01

Fast and lightVision

MiniMax · Released January 2025 · Knowledge cutoff March 2024

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...

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: 1.0M tokens
Input price: 2.2 credits / 1M tokens ($0.20 raw)
Output price: 12.1 credits / 1M tokens ($1.10 raw)
Vision (image input): Yes
Tool calling: No
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-01 now

Or open Zeplik with MiniMax-01 already selected

What MiniMax-01 is best for

High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
Working with images: screenshots, charts, photos and scanned documents alongside text

Example prompts

Prompts that suit a fast and light model like MiniMax-01:

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 (batch)	524K	3.3	13.2	May 2026
MiniMax M3 (free)	1.0M	0	0	May 2026
MiniMax M3	524K	3.3	13.2	May 2026
MiniMax M2.7	205K	3.3	13.2	March 2026
MiniMax M2.7 (free)	197K	0	0	March 2026
MiniMax M2.5	200K	3.0	11.9	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	6.0	24.2	June 2025

All 11 MiniMax models

Frequently asked questions

What is MiniMax-01?: MiniMax-01 is an AI model by MiniMax. MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...
How much does MiniMax-01 cost on Zeplik?: Input tokens cost 2.2 credits per million and output tokens 12.1 credits per million (1 credit = $0.10; the raw provider rates are $0.20 and $1.10 per million). New accounts start with free credits.
How long can a conversation with MiniMax-01 be?: MiniMax-01 has a 1.0M-token context window (1,000,192 tokens), which covers the conversation plus any documents you attach.
Does MiniMax-01 support images and tools?: MiniMax-01 accepts image input and does not support tool calling.

Related models

MiniMax M3 (batch)Fast and light

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,...

524K ctx13.2 cr/M outMay 2026

MiniMax M3 (free)Fast and light

1.0M ctx0 cr/M outMay 2026

MiniMax M3Fast and light

524K ctx13.2 cr/M outMay 2026

MiniMax M2.7Fast and light

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...

205K ctx13.2 cr/M outMarch 2026

MiniMax M2.7 (free)Fast and light

197K ctx0 cr/M outMarch 2026

MiniMax M2.5Fast and light

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...

200K ctx11.9 cr/M outFebruary 2026