BaseRTBase Compute
|
Cloudflare AI GatewayCloudflare
|
|||||
Related Products
|
||||||
About
BaseRT is a high-performance LLM inference runtime for Apple Silicon that lets developers pull models from Hugging Face, chat with them locally, or serve an OpenAI-compatible API from one CLI. Accelerated by hand-written Metal kernels, it is designed to deliver fast prefill and decode performance on M-series Macs, with published benchmarks showing up to 6.4× faster prefill than llama.cpp, 3.9× faster than MLX, and up to 1.33× faster decode. The basert CLI handles model downloading, conversion, interactive chat, serving, completion, benchmarking, inspection, and bundle signing. Its server supports chat, completions, embeddings, transcription, tool calls, continuous batching, paged KV caching, and prefix caching, while supported models can process text, vision, and audio. BaseRT uses its own .base model format with Q2–Q8 affine quantization, optional AWQ calibration, and signed bundles, and can convert GGUF, Hugging Face, and MLX checkpoints.
|
About
Cloudflare AI Gateway is an intelligent control plane for AI applications, built to connect to any model, dynamically route requests, and manage usage, billing, and logs from one unified gateway. It gives teams visibility and control over AI apps by connecting applications to AI Gateway, gathering insights on how people are using the application through analytics and logging, and controlling how the application scales with caching, rate limiting, request retries, model fallback, and more. AI Gateway helps reduce cost and latency by caching responses and reducing redundant API calls, so frequent requests can be served directly from Cloudflare’s cache instead of the original model provider. It improves reliability with dynamic controls that configure how and when model provider APIs are called based on attributes, fallbacks, latency, cost, or availability, with routing rules that can be adjusted from the dashboard or API without redeployments or downtime.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
AI infrastructure engineers and developers seeking a fast, private local model inference and an OpenAI-compatible backend for applications and coding agents
|
Audience
Developers and AI teams that need to route, monitor, control, and optimize requests across multiple AI models and providers
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
$20 per month
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationBase Compute
Founded: 2026
Australia
www.basecompute.co/getbasert
|
Company InformationCloudflare
Founded: 2009
United States
www.cloudflare.com/products/ai-gateway/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
|
|||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Gemma 4
Claude Opus 4.7
Cloudflare
GPT-5.5
Gemma 3
Hugging Face
Kimi K2.6
Llama 3.1
Llama 3.2
Mistral AI
|
Integrations
Gemma 4
Claude Opus 4.7
Cloudflare
GPT-5.5
Gemma 3
Hugging Face
Kimi K2.6
Llama 3.1
Llama 3.2
Mistral AI
|
|||||
|
|
|