MiniMax: MiniMax-01

Text input Image input Text output
Author's Description

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 of up to 4 million tokens. The text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model. To read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2

Key Specifications
Cost
$$$
Context
1M
Parameters
456B (Rumoured)
Released
Jan 14, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Top P Max Tokens Temperature
Performance Summary

MiniMax-01, released on January 14, 2025, is a powerful multimodal AI model combining text generation (MiniMax-Text-01) and image understanding (MiniMax-VL-01). It features a substantial 456 billion parameters, with 45.9 billion activated per inference, and an impressive context length of up to 4 million tokens. The model consistently ranks among the fastest, demonstrating exceptional speed across 8 benchmarks. It also offers competitive pricing, placing in the 60th percentile across 7 benchmarks. Notably, MiniMax-01 exhibits outstanding reliability, achieving a 100% success rate across all 8 benchmarks, indicating minimal technical failures. In terms of performance across categories, MiniMax-01 shows strong capabilities in Ethics (100% accuracy), General Knowledge (99% accuracy), Email Classification (99% accuracy), Instruction Following (65% accuracy), and Reasoning (74% accuracy). It stands out for its perfect ethical responses, making it the most accurate model at its price point and among models of similar speed. However, a significant weakness is observed in Mathematics, where it scored 0% accuracy. Its performance in Hallucinations is also a concern, with only 56% accuracy, suggesting a tendency to generate information for fictional concepts rather than acknowledging uncertainty. Coding performance is moderate at 81% accuracy.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $1.1

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Minimax
Minimax | minimax/minimax-01 1M $0.2 / 1M tokens $1.1 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by minimax