Open-source Mac app that runs AI models locally — private, offline, and free. Add cloud models when needed.
AI inference — AI tools
283 tools in this categoryInfrastructure for running models in production: serve checkpoints behind an API, rent GPUs by the second, batch large jobs, and watch latency and cost per request. Sits after the training stage — this is where a model becomes something an app can call.
Platform to deploy, manage, and scale AI models on your own infrastructure — from local servers to multi-cloud setups.
Cloud API for face recognition, detection, age/gender/emotion analysis, and AI-generated baby/aging predictions.
Run ComfyUI workflows online without expensive hardware — deploy AI applications with one-click API generation
Compare and deploy GPU instances across 30+ cloud providers from a single console.
A unified AI API gateway offering access to multiple text, image, and video models with cost savings and network acceleration.
Self-hosted AI platform — deploy LLMs, vector databases, and Jupyter notebooks on your own infrastructure in seconds.
A friendly JavaScript library that brings machine learning models for pose, image, and sound recognition directly into your web browser.
Open-source platform to provision GPUs and orchestrate AI workloads across clouds, Kubernetes, and on-prem clusters.
Enterprise gateway to manage, secure, and monitor access to 250+ LLMs and MCPs with built-in governance and observability.
Build and deploy ultra-low-power AI models on Nordic devices — no ML expertise required.
Access large language, text-to-image, and speech models via REST API and playground
Eco-friendly HPC data center providing GPU computing power and AI infrastructure for developers and businesses
API for running open-source LLMs — up to 80% cheaper than competitors, with high throughput and privacy-first handling.
On-demand access to NVIDIA H100, H200, and AMD MI300 GPU cloud clusters for AI and deep learning workloads.
Seedream 2.0 is the foundation model powering the AI image features in Doubao & Dreamina, offering native Chinese-English image generation and outperforming leading models in text rendering.
Access over 100 leading text, image, and video AI models through a single, OpenAI-compatible API.
Full-stack AI platform for building and deploying long-horizon agentic systems with inference, compute, and agent environments.
Rent dedicated GPU servers and VPS for AI, rendering, and LLM hosting, starting at $85/month.
AI-powered identity verification SDKs for face recognition, liveness detection, ID document scanning, and deepfake detection.
Optimize open-source AI models for production — benchmark engines, tune latency, and deploy on any GPU.
A German-based AI services company offering custom AI software development, consulting, and training for businesses.
Unified API gateway for 100+ AI models — access, compare, and integrate multiple providers with a single endpoint.
Open-source AI library for Node.js — pre-trained models for embeddings and classification with optimized cold-start performance