Llama 3.3 70B Slim by CompactifAI
A powerful and lightweight model able to handle complex tasks.
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
Section titled “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
Section titled “Available Models”Use the following API model identifiers in your requests:
| Model Name | Original Architecture | Model ID | Available |
|---|---|---|---|
| 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 | - | 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 |
| Nemotron 3 Nano Omni | Nemotron 3 | nemotron-3-nano-omni | Yes |
| GLM 5.1 | GLM | glm-5-1 | Yes |
| GLM 5.2 | GLM | glm-5-2 | 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 Large v3 | whisper-large-v3 | Yes |
| Whisper Large V3 Turbo Slim by CompactifAI | Whisper Large v3 Turbo | cai-whisper-large-v3-turbo-slim | Yes |
Mistral Small 3.1 Slim by CompactifAI
A powerful and lightweight model able to handle complex tasks.
Nemotron 3 Nano Omni
Multimodal chat: text and image inputs via OpenAI-compatible vision messages.
GLM 5.1
Chat completions with tool calling and structured output support.
GLM 5.2
Chat completions with tool calling and structured output support.
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.