High-performance AI cloud platform for training, inference, and data science with sovereign data centers in Canada and USA
AI inference — AI tools
262 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.
A network for AI agents to discover, connect, and communicate with each other autonomously.
A unified API platform that gives developers one key to access over 200 AI models for image, video, and text generation.
Drop-in proxy that monitors, optimizes, and protects your LLM spending across apps and coding agents
Zhipu AI's 745B parameter language model for advanced reasoning, coding, and agentic tasks — accessible via API and web platform.
High-performance vector database for AI workloads — fast similarity search, metadata filtering, and optional compression.
A unified API for over 400 AI models, offering optimized inference, cost reduction, and enterprise-grade reliability.
Unified API for 20+ AI image & video models — access Flux, Kling, Veo, and more with one integration.
Nexa SDK runs any model on any device, across any backend locally—text, vision, audio, speech, or image generation—on NPU, GPU, or CPU. It supports Qualcomm, Intel, AMD and Apple NPUs, GGUF, Apple MLX, and the latest SOTA models (Gemma3n, PaddleOCR).
Private inference endpoint for coding agents — zero data retention, EU-hosted, open-weight models.
Unified API gateway providing access to 100+ AI models (text, image, video, audio) with intelligent routing and monitoring.
On-demand GPU rental service for AI training, machine learning, and high-performance computing workloads
Open-source desktop app that runs a P2P AI node to join a distributed intelligence network.
Cloud GPU rental platform for AI research — rent A100, RTX 4090, and other GPUs by the hour with integrated tools.
Open-source AI engineering toolkits for OCR, document processing, speech, and LLMs — ready for deployment.
AI model router — analyzes prompt difficulty, sends hard tasks to frontier models and routine work to cheaper open-source models.
High-performance compute platform for AI workloads — simplifies orchestration and reduces costs compared to legacy systems
One API for 70+ AI models — video, image, music, and LLMs — up to 46% cheaper than official APIs
On-device AI security scanner for macOS — scans code for vulnerabilities locally, no cloud needed.
Access and compare dozens of AI models from OpenAI, Google, Anthropic, and others in one interface with unified pricing.
High-speed AI inference API powered by purpose-built hardware, not repurposed GPUs.
Unified inference routing across AI providers — switch between OpenAI, Gemini, Anthropic, and others through a single interface