LLM Reference

abab Models by MiniMax

MiniMaxProprietaryProprietary
5 models2023–2024Up to 192k ctx

Details

ResearcherMiniMax
LicenseProprietary
Commercial useCommercial use with conditions
Models5
Released2023–2024
Max context192k

Links

Website

About

The "abab" family of large language models (LLMs) by MiniMax showcases advanced capabilities in processing and generating diverse content forms. Among these, the abab-video-1 model is designed for superior video generation, adeptly handling dynamic video content with high compression efficiency and realistic physics. Its versatile output spans from 3D movie scenes to 2D animations, showcasing its adaptability in various styles. Another notable model, abab 7, leverages the MOE+Linear Attention architecture to enhance processing speeds, particularly with long text sequences, surpassing even models like GPT-4o. Furthermore, it offers multimodal functionality, seamlessly integrating text, images, sound, and video processing, underlining MiniMax's commitment to developing high-performance, efficient, and versatile LLMs 3.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

5 in view
abab 6.5Current

Use when the workload needs 192k context.

2024-04192k context
abab 6.5sCurrent

Use when the workload needs 192k context.

2024-04192k context
Abab 6Current

Use when the workload needs 32k context.

2024-0132k context
Abab 6 ProCurrent

Use when provider availability and model metadata match the workload.

2024-01

Use when the workload needs 16k context.

2023-0816k context

Release Timeline

3 release groups
2024-04
2 current
abab 6.5
192k context
Current
abab 6.5s
192k context
Current
2024-01
2 current
Abab 6
32k context
Current
Current
2023-08
1 current
Abab 5 Chat
16k context
Current

Specifications(5 models)

abab model specifications comparison
ModelReleasedContext
abab 6.52024-04192k
abab 6.5s2024-04192k
Abab 62024-0132k
Abab 6 Pro2024-01
Abab 5 Chat2023-0816k

Frequently Asked Questions

What is abab used for?
abab is used for math-heavy prompts and long-context generation. The family description and listed model capabilities point to those workloads as the best fit.
How does abab compare to MiniMax Speech?
abab by MiniMax is strongest where you need math-heavy prompts, while MiniMax Speech by MiniMax is the closest related family to check for text to speech. abab has 5 listed variants and reaches up to 192k context, so compare the specs and pricing tables before choosing a production model.
Which abab model should I use?
If price is the main constraint, use the pricing table first because abab does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate abab 6.5 with 192k context.