Here you’ll get an overview of all the amazing features Humiris offers to help you mix all LLMs in 1 model.
Model | Context Window (Tokens) | Max Completion Token | Description |
---|---|---|---|
Baby1 | 128,000 | 4,096 | Optimized for cost-speed efficiency, making it ideal for rapid inference and real-time applications. |
Baby1-adv | 128,000 | 4,096 | A cost-effective, high-speed reasoning model designed for optimal performance. |
Mommy1 | 128,000 | 16000 | Specializes in contextual reasoning, problem decomposition, and structured execution of complex workflows. |
Mommy1-adv | 128,000 | 16000 | Balances accuracy and efficiency, making it versatile for structured reasoning tasks. |
Daddy1 | 200,000 | 16000 | Offers broad knowledge and deep contextual understanding, significantly reducing hallucinations and enhancing reliability across diverse topics. |
Daddy1-adv | 200,000 | 16000 | Humiris’ most advanced and intelligent AI model for STEM reasoning and complex problem-solving. Designed to push the boundaries of math, coding, and scientific analysis. |
Model | Context Window (Tokens | Max Completion Token | Description |
---|---|---|---|
codiris-v1-preview | 1M | 50,000 | Codiris, our first multimodal, post-trained engineered specifically for complex code workflows. |
codiris-v1-mini | 1M | 50,000 | Cost-efficient, post-trained built for coding |