Mistral Small 3.1 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 |
|---|---|---|---|
| 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 5.1 (Uncensored) | GLM | cai-glm-5-1 | Yes |
| GLM 5.2 | GLM | glm-5-2 | Yes |
| Quasar 438B | - | quasar-438b | Yes |
| Openai GPT OSS 120B | - | gpt-oss-120b | Yes |
| Hypernova 60B | - | hypernova-60b | Yes |
| Carina 60B | - | carina-60b | Yes |
| Qwen 3.6 27B (Uncensored) | - | qwen-3-6-27b | Yes |
| Whisper Large V3 Turbo Slim by CompactifAI | Whisper Large v3 Turbo | cai-whisper-large-v3-turbo-slim | Yes |
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 5.1 (Uncensored)
Chat completions with tool calling and structured output support.
GLM 5.2
Chat completions with tool calling and structured output support.
Quasar 438B
Chat completions with tool calling and structured output support.
Hypernova 60B by CompactifAI
A powerful and lightweight model able to handle complex tasks.
Carina 60B
A powerful and lightweight model able to handle complex tasks.
Qwen 3.6 27B (Uncensored)
A powerful and lightweight model able to handle complex tasks.
Whisper Large V3 Turbo Slim by CompactifAI
Compressed turbo Whisper: ~50% smaller, 90%+ baseline WER retained, lower cost.