MiniMax API

Every MiniMax model on EmpirioLabs AI, 6 in all. Compare them, then call the one that fits your task, quality, and pricing needs.

MiniMax Video Generation Text Generation Audio Generation 6 models

About MiniMax APIs

MiniMax on EmpirioLabs brings together 6 model APIs from MiniMax, including MiniMax M3.1 Flash, MiniMax Music 3, MiniMax H3, MiniMax M3. Each model keeps its own dedicated page with live pricing, parameters, docs, and playground access.

MiniMax models (6)

MiniMax API pricing

Compare the family at a glance, then open a model page for the complete live rate card and parameters.

Text Generation: Per 1M tokens, by input rate

ModelInputOutput
MiniMax M3.1 Flash$0.15$0.1125$0.60$0.45
MiniMax M3$0.30 <=512K $0.225 $0.60 >512K $0.45$1.20 <=512K $0.90 $2.40 >512K $1.80

Video Generation: Priced per second

ModelLowest rateApplies to
MiniMax H3 Lite$0.025 per second480p
MiniMax H3 Highspeed$0.06 per second768p
MiniMax H3$0.18 per second768p
Endpoint
POST/v1/chat/completions
Pricing
Type
Spec
Rate
Input
per 1M prompt tokens
$0.15$0.1125
Output
per 1M generated tokens
$0.60$0.45
Implicit cache read
per 1M cached input tokens
$0.015$0.01125
Web search
per call when invoked
$0.01
Best fit
Fast multimodal coding and agent model with 1M context, adjustable reasoning depth, image and video input, function calling, and built-in web search.
Endpoint
POST/v1/audio/generations
Pricing
Type
Spec
Rate
Music generation
per generated second
$0.002$0.0018
Best fit
Generates complete stereo songs from lyrics and a style prompt, with duration, seed, and format controls up to 5 minutes.
Endpoint
POST/v1/videos/generations
Pricing
Type
Spec
Rate
768p
per second
$0.18
2K
per second
$0.26
2K regeneration
per second
$0.10
Reference image input
per input image after the first 5
$0.08
Prompt expansion input
per 1M prompt tokens
$1.80
Prompt expansion output
per 1M generated tokens
$7.20
Best fit
Generates 4 to 15 second clips at up to 2K with native stereo audio, following text, image, video, and audio references in one request.
Endpoint
POST/v1/chat/completions
Pricing
Type
Spec
Rate
Input
per 1M prompt tokens
$0.30 <=512K $0.225 $0.60 >512K $0.45
Output
per 1M generated tokens
$1.20 <=512K $0.90 $2.40 >512K $1.80
Implicit cache read
per 1M cached input tokens
$0.06 <=512K $0.045 $0.12 >512K $0.09
Web search
per call when invoked
$0.01
Best fit
MiniMax M3 is a multimodal reasoning model for coding, agents, and long-context analysis with text, image, and video input.
Endpoint
POST/v1/videos/generations
Pricing
Type
Spec
Rate
768p
per second
$0.06
Reference image input
per input image after the first 5
$0.03
Best fit
Fast 4 to 15 second 768p clips with native stereo audio, from text, a first and last frame, or image, video, and audio references in one request.
Endpoint
POST/v1/videos/generations
Pricing
Type
Spec
Rate
480p
per second
$0.025
768p
per second
$0.04
Reference image input
per input image after the first 5
$0.02
Best fit
Lower-cost 4 to 15 second clips at 480p or 768p with native stereo audio, from text, a first and last frame, or image, video, and audio references.
Compare every model on the full pricing page

MiniMax examples and comparisons

See prompt tests, output notes, and comparison runs that mention this model family.

MiniMax APIs: common questions

What is the MiniMax API?

MiniMax on EmpirioLabs covers 6 model APIs from MiniMax: MiniMax M3.1 Flash, MiniMax Music 3, MiniMax H3, MiniMax M3, MiniMax H3 Highspeed, MiniMax H3 Lite. You use one EmpirioLabs API key and choose the model id that fits the request.

Which MiniMax model should I use?

Start with the model whose dedicated page matches your speed, quality, and pricing needs, then test it in the EmpirioLabs playground. The comparison cards above link to each model's live rate card and quickstart.

How is MiniMax pricing shown?

Pay as you go, or choose a plan with weekly allowances. The cards on this page show a short live-catalog summary, and each model page shows the complete rate card that matches API billing.

Which MiniMax model costs the least on EmpirioLabs AI?

MiniMax H3 Lite lists the lowest rate per second of the 3 MiniMax models priced that way, followed by MiniMax H3 Highspeed, MiniMax H3. The price table on this page shows each model's lowest rate and what it applies to.

Can I try MiniMax in the browser?

Yes. Open any model page in this family and use its playground link to test prompts and parameters in the browser before integrating the API.

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.