Model Hosting & Inference AI Tools

Flat monthly plans for LLM API access with no per-token metering, built on open models.

Enterprise gateway serving 300+ models over one encrypted, zero-retention endpoint with per-token billing

Google Cloud's platform for building, tuning, deploying and governing AI agents and models, formerly sold as Vertex AI.

Runs LLMs and vision models on encrypted GPUs so enterprise data never leaves the customer's environment.

Developer platform serving 1,000+ generative image, video and audio models through one metered API

Desktop harness that joins your own devices into an encrypted mesh, keeps a private memory of your work and trains LoRA adapters on it

Runs open-weight language models locally from one command, with a hosted tier for larger models

Open-source desktop chat app that runs open models offline or connects to cloud providers, plus a terminal coding agent.

Desktop app for downloading and running open-weight LLMs locally, now with a Bionic agent and optional US-hosted cloud models.

Ahead-of-time GPU compiler with a pay-as-you-go inference API, plus managed and on-premise deployments

On-device AI inference stack for Apple Silicon, aimed at fast, private, local model execution.

One API over 500+ image, video and audio models, billed per generation with no charge for failed jobs

Pay-as-you-go APIs for 200-plus open models, rented GPUs, and a sandbox for running agents.

Pay-per-job inference API serving 50+ image and video models with sub-200 ms image latency

Free platform for optimizing, quantizing and deploying PyTorch or ONNX models to run on Qualcomm phones, PCs, cars and IoT chips.

Serverless API for running 100+ image, video, 3D and audio models, billed per output or per second of GPU time

Trains and serves open and custom language models with per-token API pricing.

Self-hosted open-source runtime that serves text, speech, vision, image and agent workloads behind OpenAI-compatible APIs.

Prebuilt GPU-optimized model containers with standard APIs for self-hosting AI models, plus hosted endpoints for prototyping.

Pay-per-call hosting for 1,000+ image, video, audio and language models behind one API