Langfuse alternatives

Fast LLM & ML testing at scale 🛡️ Detect hallucinations & biases automatically 🔍 Enterprise Testing Hub ☁️ Self-hosted / cloud 🤝 Integrated with 🤗, MLFlow, W&B From tabular models to LLMs, Giskard handles everything! https://github.com/Giskard-AI/giskard

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

A new type of multimodal large language model (MLLM) from Apple that excels in both image understanding and language processing, particularly demonstrating significant advantages in understanding spatial references.

Calculate and compare the cost of using OpenAI, Azure, Anthropic, Llama 3, Google Gemini, Mistral, and Cohere APIs with our powerful FREE pricing calculator.

The fastest and easiest way to protect your LLM-powered applications. Safeguard against prompt injection attacks, hallucinations, data leakage, toxic language, and more with Lakera Guard API. Built by devs, for devs. Integrate it with a few lines of code.

Superpowered AI is an end-to-end knowledge retrieval solution that makes it easy to build production-ready LLM applications with access to external knowledge.

With Boogie, you can build NLP applications in minutes using automated workflows. Experiment with LLM prompts, upload proprietary data, regression test in production, tune your application and more.

Iterate is a free platform that helps you and your team save, test and share your ChatGPT prompts, all in one click. With automatic version control and built-in QA-ing of your prompts, Iterate saves you time and turns your whole team into prompt engineering experts.

AwanLLM is a cloud provider for LLM inference which focuses on cost & reliability. Unlike other providers, we don't charge per token which results in ballooning costs. Instead, we charge monthly. We achieve this by hosting our data center in strategic cities.

Signway is a gateway for redirecting short-lived signed URLs to the requested API. It its meant to be used for streaming data directly between client applications and LLM APIs in a secure way, using cryptographic signatures instead of API credentials.