BaseRT

BaseRT

Base Compute
+
+

Related Products

  • Sogolytics
    869 Ratings
    Visit Website
  • Qloo
    23 Ratings
    Visit Website
  • Convesio
    63 Ratings
    Visit Website
  • Vehicle Acquisition Network (VAN)
    54 Ratings
    Visit Website
  • ClickUp
    19,572 Ratings
    Visit Website
  • Float
    3,787 Ratings
    Visit Website
  • Concord
    237 Ratings
    Visit Website
  • IONOS Cloud GPU Servers
    45,340 Ratings
    Visit Website
  • InterProse ACE
    147 Ratings
    Visit Website
  • Titan
    378 Ratings
    Visit Website

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 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

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 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 Videos

Pricing

No information available.
Free Version Not Supported
Free Trial Not Supported

Pricing

$0.48 per output
Free Version Not Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

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 Information

Base Compute
Founded: 2026
Australia
www.basecompute.co/getbasert

Company Information

Keak
United States
cheaperinference.com

Alternatives

Alternatives

LFM2

LFM2

Liquid AI

Categories

AI Tools Supported

Categories

AI Gateways Supported
AI Inference Supported

Integrations

Claude Haiku 4.5 Not Supported
Claude Opus 5 Not Supported
Claude Sonnet 4.5 Not Supported
DeepSeek-V4.1-Flash Not Supported
GLM-4.5 Not Supported
GLM-4.5-Air Not Supported
GLM-4.7 Not Supported
GLM-5.1 Not Supported
GLM-5.2 Not Supported
GLM-5.3 Not Supported
GLM-5.3-Flash Not Supported
GPT-5.4 Not Supported
GPT-5.5 Pro Not Supported
GPT-5.6 Terra Not Supported
Gemini 3.7 Flash Not Supported
Gemini 3.8 Flash Not Supported
Kimi K3 Not Supported
Muse Spark 1.2 Not Supported
OpenAI Supported
gpt-oss-120b Not Supported

Integrations

Claude Haiku 4.5 Supported
Claude Opus 5 Supported
Claude Sonnet 4.5 Supported
DeepSeek-V4.1-Flash Supported
GLM-4.5 Supported
GLM-4.5-Air Supported
GLM-4.7 Supported
GLM-5.1 Supported
GLM-5.2 Supported
GLM-5.3 Supported
GLM-5.3-Flash Supported
GPT-5.4 Supported
GPT-5.5 Pro Supported
GPT-5.6 Terra Supported
Gemini 3.7 Flash Supported
Gemini 3.8 Flash Supported
Kimi K3 Supported
Muse Spark 1.2 Supported
OpenAI Not Supported
gpt-oss-120b Supported
Claim BaseRT and update features and information
Claim BaseRT and update features and information
Claim Cheaper Inference and update features and information
Claim Cheaper Inference and update features and information