I created It is a web-based, side-by-side comparison sandbox designed for developers to test and evaluate different

Homeby Cheryl2026-09-16

I created https://LLMCode.ai It is a web-based, side-by-side comparison sandbox designed for developers to test and evaluate different Large Language Models. Key Features: It allows users to compare models like GPT, Claude, Gemini, Llama, and Qwen simultaneously using their own API keys.Pricing & Data: The lab interface itself is free, requires no signup or credit card, and calculates exact direct provider token costs before running queries. API keys remain stored locally within the browser.

Links

LLMCode Lab — Compare AI Models Side-by-Sidellmcode.aiCompare OpenAI, Claude, Gemini, NVIDIA, and HuggingFace models side-by-side in your own testing lab — bring your own API key.

open source discussion

More in Home

I tried to create a latent context layer that is a warmed up version of a small LDA Topic model that is injectable into the context window via memories or system prompts.I made some CVSS classification scripts that use Jev to generate a CVSS vector for a given software vulnerability description.Jev can be used for profiling players, which is great for organizing playtests and checking balance changes across different player groups.