GPT models via OpenAI API

Claude models via Anthropic API

Claude models via Google Cloud Vertex AI

Gemini models via Google AI API

Enterprise Gemini models via Google Cloud Vertex AI

Azure-hosted OpenAI models

AWS Bedrock models (Claude, Llama, Titan)

Grok models by xAI

Mistral Large and Codestral models

Command R+ models with RAG support

Ultra-fast inference with browser search

Fast LLM inference platform

Wide selection of open-source models

Serverless AI inference on Cloudflare edge network

Reasoning models with context caching

Specialized hardware acceleration

Cost-effective model hosting

Search-augmented language models

Community models and custom deployments

Model deployment platform

Inference API and serverless endpoints

Unified API for 100+ models

AI gateway with observability, caching, and load balancing

Community-powered distributed inference via Ollama and LM Studio

Connect to remote WebInfer gateway servers for federated inference

High-performance local LLM inference with llama.cpp server

Local models via LM Studio server

Local models via Ollama

Browser-native Transformers models with WebGPU

Downloaded models running locally with WebGPU

Local image generation with ComfyUI workflows

Stable Diffusion WebUI with extensive customization

Simplified image generation with built-in enhancements

Professional creative workflow for image generation

On-device AI with Chrome built-in Gemini Nano model

Voice synthesis and cloning

Speech-to-text and transcription

Real-time speech transcription

Local audio generation via Python inference engine (Stable Audio Open)

Fast image and video generation

FLUX image generation models

Video generation (Dream Machine)