Models Catalog

Welcome to our Models Catalog, where you can explore our collection of cutting-edge compressed language models. CompactifAI API delivers a new class of compressed, ultra-efficient AI models engineered for performance, sustainability, and adaptability. These dramatically reduce compute and energy costs while maintaining enterprise-grade accuracy and speed. It adapts seamlessly to diverse environments, ensuring consistent, high-performance AI. With turnkey software and an intuitive API, it offers cost effective inference enabling enterprises to innovate faster, scale cost-effectively, and unlock competitive edge.

Compression Benefits

Dramatic Cost Reduction: Up to 70% lower inference costs compared to uncompressed models through optimized resource utilization
Massive Throughput Gains: Process up to 4x more requests per second with compressed models requiring fewer computational resources
Low-Latency Inference: Achieve faster response times due to reduced model size and optimized memory usage
Minimal Quality Loss: Advanced compression techniques preserve model performance with typically <5% benchmark difference
Superior Concurrency: Support significantly more simultaneous users and requests with the same hardware resources
Resource Efficiency: Reduced memory footprint and computational requirements enable better hardware utilization

Available Models

Use the following API model identifiers in your requests:

Model Name	Original Architecture	Model ID	Available
Llama 4 Scout Slim by CompactifAI	Llama 4 Scout	cai-llama-4-scout-slim	Yes
Llama 4 Scout	-	llama-4-scout	Yes
Llama 3.3 70B Slim by CompactifAI	Llama 3.3 70B	cai-llama-3-3-70b-slim	Yes
Llama 3.3 70B	-	llama-3-3-70b	Yes
Llama 3.1 8B Slim by CompactifAI	Llama 3.1 8B	cai-llama-3-1-8b-slim	Yes
Llama 3.1 8B Slim Reasoning by CompactifAI	Llama 3.1 8B	cai-llama-3-1-8b-slim-r	Yes
Llama 3.1 8B	-	llama-3-1-8b	Yes
Mistral Small 3.1 Slim by CompactifAI	Mistral Small 3.1	cai-mistral-small-3-1-slim	Yes
Mistral Small 3.1	-	mistral-small-3-1	Yes
Openai GPT OSS 20B	-	gpt-oss-20b	Yes
Openai GPT OSS 120B	-	gpt-oss-120b	Yes
Hypernova 60B	-	hypernova-60b	Yes
Blackstar 10B	-	blackstar-10b	Yes
Whisper Large V3	Whisper	whisper-large-v3	Yes
Whisper Large V3 Turbo Slim by CompactifAI	Whisper Large V3	whisper-large-v3-turbo-slim	Yes

Llama 4 Scout Slim by CompactifAI

Powerful model for long context tasks.

Llama 3.3 70B Slim by CompactifAI

A powerful and lightweight model able to handle complex tasks.

Llama 3.1 8B Slim by CompactifAI

Good model for simple general purpose tasks requiring low latency.

Mistral Small 3.1 Slim by CompactifAI

A powerful and lightweight model able to handle complex tasks.

Hypernova 60B by CompactifAI

A powerful and lightweight model able to handle complex tasks.

Blackstar 10B by CompactifAI

A powerful and lightweight model able to handle complex tasks.

Whisper Large V3

Speech-to-text model optimized for multilingual transcription.

Whisper Large V3 Turbo Slim by CompactifAI

Compressed turbo Whisper: ~50% smaller, 90%+ baseline WER retained, lower cost.