Help developers discover the tools you use. Get visibility for your team's tech choices and contribute to the community's knowledge.
It is a state-of-the-art LLM for converting natural language questions to SQL queries. It has been fine-tuned on hand-crafted SQL queries in increasing orders of difficulty. It significantly outperforms all major open-source models and slightly outperforms gpt-3.5-turbo. | Try Grok 4 on GPT Proto. Access xAI’s most advanced 1.7T LLM with 130K context, multimodal support, and real-time data integration for dynamic analysis. |
LLM for SQL generation;
Significantly outperforms all major open-source models;
Fine-tuned implementation of StarCoder | grok-4, grok-4 api, grok ai |
Statistics | |
GitHub Stars 3.9K | GitHub Stars - |
GitHub Forks 266 | GitHub Forks - |
Stacks 1 | Stacks 3 |
Followers 1 | Followers 3 |
Votes 0 | Votes 1 |
Integrations | |
| No integrations available | |

Flow Video Generator delivers 4K cinematic quality with Google Flow Video motion synthesis, multi-shot storytelling, lightning-fast generation, and unparalleled realism. Create stunning Flow AI Video 4K from text or images with Flow AI Video Free Online trials. Flow Video Maker for professional video creation.

It is the base model weights and network architecture of Grok-1, the large language model. Grok-1 is a 314 billion parameter Mixture-of-Experts model trained from scratch by xAI.

On the web: create Sora video from text and images. Try Sora 2 web (sora2 web) to generate videos online, or integrate with the Sora 2 API

Powered by advanced AI models. Transform text into professional music instantly. No subscriptions required - start creating now!

Turns any prompt into a cinematic-ready clip. Type an idea, drop in reference images, and get a polished video alongside invite code updates and compliance guidance.

Unleash your creativity with letsmkvideo, the leading AI video generator. Effortlessly create professional videos from text, animate photos, and create stunning AI video effects. Get started for free—no watermarks, just high-quality results in minutes.

It is Google’s largest and most capable AI model. It is built to be multimodal, it can generalize, understand, operate across, and combine different types of info — like text, images, audio, video, and code.

It is a state-of-the-art foundational large language model designed to help researchers advance their work in this subfield of AI.

It is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Create polished visuals and clips in the browser with Nano Banana Pro using text prompts or reference images.