Venice: Uncensored (free)

Venice Uncensored Dolphin Mistral 24B Venice Edition is a powerful, fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model stands out as an “uncensored” instruct-tuned LLM, providing users with complete control over alignment, system prompts, and overall behavior. It's specifically designed for advanced and unrestricted applications, emphasizing steerability and transparent operation by removing default safety and alignment layers common in mainstream assistant models. This model offers a generous context window of 32K tokens and a maximum output of 4K tokens, making it suitable for complex tasks. It supports capabilities like code generation and streaming, and excels in chat, code, and translation. Best of all, it's completely free to use, with pricing at $0.00 per 1M tokens for both input and output. Please note, it does not support image generation or internet access.