CompactifAI·Inference API

Frontier intelligence at an unbeatable price

Multiverse Computing's CompactifAI API gives developers a curated catalog of frontier-class models, combining our own leading models with select third-party models, optimized for coding and output-heavy workloads, at a fraction of typical market cost.

View ModelsRead Documentation

Why our API?

Lowest Cost for Open-Source Models

Strongest Throughput & TTFT-to-Price Performance Ratio

Plug & Play, No Infrastructure Needed

Scalable Enterprise Deployment & Billed per Usage

Private Endpoints Available on Private Offer

Model Catalog

CompactifAI Only
Market-Leading Price
TOP Speed-to-Price Ratio
Best Value
Multimodal
GLM 5.2
GLM 5.2
New
Input Cost
$1.10/M
Output Cost
$3.5/M
Buy with
Buy with
GLM 5.1
GLM 5.1
Input Cost
$0.95/M
Output Cost
$3.15/M
Buy with
Buy with
GLM 5.1 Uncensored
GLM 5.1 Uncensored
CompactifAI
New
Input Cost
$1.00/M
Output Cost
$3.00/M
Buy with
Buy with
Qwen 3.6 27B Uncensored
Qwen 3.6 27B Uncensored
CompactifAI
New
Input Cost
$0.15/M
Output Cost
$0.90/M
Buy with
Buy with
Hypernova 60B
Hypernova 60B
CompactifAI
Input Cost
$0.04/M
Output Cost
$0.14/M
Buy with
Buy with
Carina 60B
Carina 60B
CompactifAI
New
Input Cost
$0.05/M
Output Cost
$0.08/M
Buy with
Buy with
OpenAI gpt-oss-120b
OpenAI gpt-oss-120b
Input Cost
$0.05/M
Output Cost
$0.23/M
Buy with
Buy with
Whisper Large V3 Turbo Slim
Whisper Large V3 Turbo Slim
CompactifAI
Transcription Cost
$0.000134/Min
Buy with
Buy with
Nemotron 3 Nano Omni
Nemotron 3 Nano Omni
Input Cost
$0.20/M
Output Cost
$0.80/M
Buy with
Buy with
Mistral Small 3.1
Mistral Small 3.1
Input Cost
$0.11/M
Output Cost
$0.17/M
Buy with
Buy with
Mistral Small 3.1 Slim
Mistral Small 3.1 Slim
CompactifAI
Input Cost
$0.05/M
Output Cost
$0.08/M
Buy with
Buy with

Need a Private Endpoint or Have Questions?

Our team is ready to help you with custom deployments, private offers, and any technical questions you may have.

About Private Deployment