Category · 16 tools
Model providers, inference and SDKs — the building blocks for putting AI inside what you ship.
16 shown
The API for the Claude family of models, with long context, tool use and prompt caching.
Strong at coding, careful reasoning and long context — and the engine behind a lot of the agent tools in this library. Pay-per-token; prompt caching keeps repeat costs down.
Visit ↗A voice AI platform for realistic text-to-speech, voice cloning and dubbing via API.
The best-sounding text-to-speech and voice cloning around, with a clean API. The default when your app needs a voice that doesn't sound like a robot.
Visit ↗An inference platform optimised for fast generative media models like image and video.
The go-to for fast image and video generation behind an API. If you're building a media-gen feature, its speed and model selection are hard to beat; you pay per use.
Visit ↗Google's home for the Gemini API, with a browser playground and a free tier.
The fastest way to try Gemini and ship it — a genuinely useful free tier and a very long context window. Worth keeping in your back pocket even if another model is your default.
Visit ↗An inference platform running open models on custom LPU hardware for very fast responses.
Absurdly fast inference for open models — tokens stream so quickly it changes what feels possible in a UI. The free tier is enough to feel the speed; reach for it when latency is the product.
Visit ↗The hub for open-source models, datasets and Spaces, with hosted inference.
The GitHub of machine learning — where open models live and where you go to find, host or demo one. Essential to know even if you mostly call hosted APIs.
Visit ↗A framework for building LLM applications and agents, with LangSmith for observability.
The big, batteries-included framework for chains and agents — powerful, but sometimes more abstraction than a simple app needs. Great when your pipeline is genuinely complex; overkill when it isn't.
Visit ↗A data framework for connecting LLMs to your own data for RAG and agents.
The framework built around getting your data into a model — indexing, retrieval, RAG. Reach for it when the hard part is your documents, not the prompt.
Visit ↗A desktop app for discovering, downloading and running local LLMs with a chat UI and server.
A friendly desktop app for running local models, with a built-in chat and an OpenAI-compatible server. The GUI counterpart to Ollama when you'd rather click than type.
Visit ↗A European model provider with open-weight and commercial models via its La Plateforme API.
Strong open-weight models and a clean API, with a European data story some teams need. A credible, often cheaper alternative to the big two.
Visit ↗A tool to download and run open-source LLMs locally with a simple command and API.
Run capable open models on your own machine with one command — no cloud, no bill. The easiest on-ramp to local AI for privacy, offline work and tinkering.
Visit ↗The API platform for GPT models, plus image, audio and embedding endpoints.
The model API most apps reach for first — broad capabilities, great docs, a huge ecosystem. You pay per token with no real free tier, so mind the meter as you scale.
Visit ↗A unified API that routes requests to hundreds of models from many providers.
One API key, one bill, hundreds of models — switch providers without rewriting anything. The pragmatic way to stay model-agnostic, and some models are free.
Visit ↗A platform to run and fine-tune open-source models via API, billed per second of compute.
The easiest way to run thousands of open-source models — image, video, audio — behind one API without managing GPUs. Pay per run; great for adding a model feature without the infra.
Visit ↗An inference and fine-tuning platform for a large catalogue of open-source models.
A broad, affordable home for open-model inference and fine-tuning. A solid pick when you want open models at scale without running your own GPUs.
Visit ↗An open-source TypeScript toolkit for building AI apps with streaming and a unified model API.
Makes streaming, tool calls and swapping models a one-liner. If you're building AI features in React or Next, this is the layer to start from — free and open source.
Deep dive →