BaseRTBase Compute
|
Cheaper InferenceKeak
|
|||||
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
Cheaper Inference is an OpenAI-compatible API gateway that provides access to AI models from multiple providers through a single API key, without requiring users to change their request format. Developers can switch by replacing the provider base URL and API key while keeping the same model, messages, tools, streaming settings, and response handling. It supports text and image models, vision-capable chat requests, streaming, prompt caching, reasoning controls, and temporary image uploads for larger vision payloads. Models are selected per request, and the catalog can be filtered by type, vision, reasoning, streaming, or provider. Automatic retries handle network and provider failures, while eligible fallback routes can be tried before a request fails. Every request is visible in History, giving teams a record of request volume, token usage, and operational activity.
|
|||||
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
AI teams and developers in need of a tool to access and route requests across multiple AI models and providers through one OpenAI-compatible API
|
|||||
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
$0.48 per output
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 InformationKeak
United States
cheaperinference.com
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
|
|||||
Categories |
Categories |
|||||
Integrations
Claude Opus 4.5
Claude Opus 4.6
Claude Sonnet 4.5
Claude Sonnet 4.6
DeepSeek-V4-Pro
GLM-5
GPT-4.1 nano
GPT-5.2-Codex
GPT-5.4 Pro
GPT-5.5
|
Integrations
Claude Opus 4.5
Claude Opus 4.6
Claude Sonnet 4.5
Claude Sonnet 4.6
DeepSeek-V4-Pro
GLM-5
GPT-4.1 nano
GPT-5.2-Codex
GPT-5.4 Pro
GPT-5.5
|
|||||
|
|
|