BaseRT

BaseRT

Base Compute
+
+

Related Products

  • Sogolytics
    869 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
  • Compute with Hivenet
    4 Ratings
    Visit Website
  • Titan
    378 Ratings
    Visit Website
  • LTX
    182 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

Jectora is an OpenAI-compatible AI gateway built for organizations. One API (the Jectora API base URL) routes requests across models from multiple providers with smart routing, hardware-aware inference optimization, and intelligent caching for lower cost and latency. Keep the official OpenAI JavaScript or Python SDK: set the Jectora base URL and API key, then choose a model by ID. Chat Completions, Responses, Embeddings, and model discovery are supported; capabilities vary by model. Organization workspaces separate API keys, balance, usage, and billing. Scope each key by model, spend, expiration, or source IP. The Dashboard shows spend, requests, and tokens. Pricing is pay as you go: $0 monthly fee, no minimum spend, prepaid credits with no fixed expiration while active, and no subscription, platform fee, or long-term commitment. Unit prices are in the model catalog (USD per 1M tokens for token-based models). Sign in with GitHub. Docs and support are on the Jectora website.

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 and organizations building AI applications, including teams that need shared balance, usage and billing for AI model access

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 Not 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 monthly platform fee and no minimum spend. Add prepaid credits and pay for usage at the published model-specific rates; token, cached-token, audio, image, and video usage may use different units.
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 Not 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

Jectora
United States
jectora.com

Alternatives

Alternatives

boldrouter

boldrouter

Cybrient Technologies
DeepInfer

DeepInfer

DeepSeek
OwlVigil

OwlVigil

Syrovex

Categories

AI Tools Supported

Categories

AI Gateways Supported

Integrations

OpenAI Supported
Gemma 3 Supported
Gemma 4 Supported
Hugging Face Supported
Llama 3.1 Supported
Llama 3.2 Supported
Mistral AI Supported
Phi-3 Supported
Qwen3 Supported
Qwen3.5 Supported
Qwen3.6 Supported

Integrations

OpenAI 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
Phi-3 Not Supported
Qwen3 Not Supported
Qwen3.5 Not Supported
Qwen3.6 Not Supported
Claim BaseRT and update features and information
Claim BaseRT and update features and information
Claim Jectora and update features and information
Claim Jectora and update features and information