Model Providers & Inference

Alibaba's family of open-weight models.

AI safety company behind Claude.

Compare 50+ AI models at once for the best results.

Production-grade model inference infrastructure.

On-device AI with cloud fallback. Cactus post-trains models to know when they are wrong and hand off to frontier cloud models — cutting inference costs up to 5x.

Wafer-scale chips and ultra-fast inference.

ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration - OpenBMB/ChatDev

Enterprise AI models and the North agent platform.

Low-cost serverless inference for open models.

Open-weight frontier models from China.

Serverless inference for generative media models.

Fast generative AI inference platform.

Google's AI lab behind Gemini.

Ultra-fast LPU inference for open models.

The hub for open-source models, datasets, and agents.

Open-access AI cloud for inference and compute.

Jan is an open-source alternative to ChatGPT. Run open-source AI models locally or connect to cloud models like GPT, Claude and others.

GPU cloud for AI training and inference.

⌘ Langbase is the Serverless AI developer platform and developer experience to build, collaborate, and deploy any AI agents, apps, and AI features. The most powerful serverless platform for building A

Unified interface and proxy for 100+ LLM APIs.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

This application starts a Redis server to store and manage data. No input is required from the user. The result is a running Redis server ready to use for data storage and retrieval.

Desktop app for running local LLMs.

Up to 60 vCPUs, 240 GB RAM & GPUs. Designed for agents using CLI or MCP. Billed by the minute.

This application lets you ask health-related questions and get helpful answers from an AI assistant. You can type your medical concerns or symptoms, and the system will provide informative response...

Meta's AI division behind Llama.

Chinese AI lab with open-weight models and agents.

European frontier AI lab with open models.

Chinese AI lab behind the Kimi models.

ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate - composable-models/llm_multiagent_debate

AI cloud built on large-scale NVIDIA clusters.

Nexa AI is now part of Qualcomm AI Hub. Exciting updates coming soon.

Model APIs and GPU cloud for AI builders.

Run open models locally with one command.

Frontier AI lab behind GPT models and ChatGPT.

Build, fine-tune, and deploy custom AI models for better performance and lower costs.

Unified API gateway across hundreds of models.

OpenTag is the model-agnostic Claude Tag: eighty models to route to, up to 70% off what a tagged task costs, and never in the business of selling you tokens.

Phala Cloud delivers confidential AI on TEE-protected GPUs — private LLM inference, sealed agents, and verifiable compute on Intel TDX + NVIDIA H100/H200.

Cloud API for running open-source models.

AI chips and enterprise inference platform.

Fast serving framework for LLMs and agents.

Cloud platform for open-source model inference.

High-throughput open-source LLM serving engine.

Elon Musk's AI company behind Grok.

Chinese lab behind the GLM model family.