BaseRTBase Compute
|
RelaySwitchUplink Switch
|
|||||
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
RelaySwitch is a hosted AI model API gateway for developers who want to call models from multiple providers through a shared endpoint and account. It exposes an OpenAI-compatible API and supports the Anthropic Messages format for Claude models, allowing compatible SDKs and developer tools to connect by changing the base URL and API key. Its catalog covers chat, image, video, speech and 3D models, with model identifiers and token rates. Usage is billed from a prepaid USD balance; input and output rates are listed separately, and cached input may cost less where supported. Customers can add funds through supported card and digital-asset payment methods, without a monthly subscription. RelaySwitch is intended for developers and teams building applications and agents with hosted AI models, and provides API documentation, model listings and setup guides for supported SDKs and tools.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Supported
Linux
Not Supported
Cloud
Not Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
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, startups and agencies that call LLM APIs and want one key, prepaid billing and crypto or card payment.
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
API
Offers API
Supported
|
API
Offers API
Supported
|
|||||
Screenshots and Videos |
Screenshots and VideosNo images available
|
|||||
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Pricing
$10 prepaid
A $10 minimum prepaid top-up adds USD credit. Usage is deducted at model-specific input and output token rates; cached input may have a separate rate where supported. The service has no monthly subscription, and unused balance does not expire. Top-ups accept cards and supported cryptocurrencies, including USDT, USDC, BTC, ETH and SOL.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationBase Compute
Founded: 2026
Australia
www.basecompute.co/getbasert
|
Company InformationUplink Switch
Founded: 2026
United States
relayswitch.io
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
|
|||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
OpenAI
Supported
Anthropic
Not Supported
Claude Code
Not Supported
Cursor
Not Supported
Gemma 3
Supported
Gemma 4
Supported
Hugging Face
Supported
Llama 3.1
Supported
Llama 3.2
Supported
Mistral AI
Supported
|
Integrations
OpenAI
Supported
Anthropic
Supported
Claude Code
Supported
Cursor
Supported
Gemma 3
Not Supported
Gemma 4
Not Supported
Hugging Face
Not Supported
Llama 3.1
Not Supported
Llama 3.2
Not Supported
Mistral AI
Not Supported
|
|||||
|
|
|