Mistral Small 4 TL5

Mistral Small 4 is Mistral AI's open-weight multimodal model combining everyday instruction following, deep reasoning, and agentic coding in one system. Its Mixture-of-Experts architecture contains 119B parameters across 128 experts, selecting four per token and activating 6.5B parameters. With a 256K-token context window, it accepts text and images and generates text for document parsing, visual analysis, codebase exploration, research, and enterprise assistants. Developers can switch reasoning effort between none for fast responses and high for complex tasks. Native function calling and structured JSON output support coding agents and automated workflows. Optimized inference options include an Eagle speculative-decoding head and NVFP4 weights. The model is released under Apache 2.0 for commercial use.

INPUT

Chat templates

System Prompt:

Reasoning Effort

Top K

Top P

Temperature

Maximum response length in tokens

Progress

Console Output

Disclaimer: The content generated with this demonstration platform ("playground") is generated with AI. AI can make mistakes. The services of AKI.IO are offered exclusively for business and professional use. Creating a company account is required for commercial use. The content provided on this playground platform is for informational and educational purposes only, and its use is at your own risk. We do not assume any liability for the accuracy, completeness, or usefulness of the information provided. Viewer discretion is advised as the content may contain explicit material. This playground platform is intended for research and demonstration purposes only and should not be used as a substitute for professional advice. By using or accessing this platform, you agree to these terms and conditions.