Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
BaseRT offers a robust inference runtime for LLMs specifically optimized for Apple Silicon, allowing developers to seamlessly access models from Hugging Face, engage in local conversations, or utilize an API compatible with OpenAI through a single command-line interface. Enhanced by meticulously crafted Metal kernels, BaseRT aims to provide exceptional prefill and decoding efficiency on M-series Macs, with benchmark results indicating it performs up to 6.4 times faster in prefill tasks compared to llama.cpp, 3.9 times faster than MLX, and achieves a decoding speed that is 1.33 times quicker. The basert CLI is equipped to manage tasks such as model downloading, conversion, interactive chat, serving capabilities, completion generation, benchmarking, inspection, and bundle signing. Its server functionalities are extensive, encompassing chat interactions, text completions, embeddings, transcription services, tool calls, continuous batching, paged key-value caching, and prefix caching, with support for models that can handle text, vision, and audio data. BaseRT employs a proprietary .base model format that incorporates Q2–Q8 affine quantization, optional AWQ calibration, and signed bundles, and it is capable of converting GGUF, Hugging Face, and MLX checkpoints. Furthermore, this innovative runtime is tailored to maximize the capabilities of Apple Silicon, making it an essential tool for developers in the AI space.
Description
Cheaper Inference serves as an API gateway compatible with OpenAI, enabling users to access various AI models from different providers through a unified API key, thus eliminating the need for any changes in request formatting. Developers have the flexibility to switch providers simply by updating the base URL and API key while retaining the same model, messages, tools, streaming configurations, and response management. This service accommodates both text and image models, facilitates vision-enabled chat requests, offers streaming capabilities, includes prompt caching, provides reasoning controls, and allows temporary image uploads for more extensive vision data. Each request can have its model selected individually, and users can filter the catalog based on model type, vision capabilities, reasoning options, streaming availability, or provider identity. The system includes automatic retries to manage network disruptions and provider errors, with fallback routes available for eligible requests to prevent failures. Additionally, every request is documented in the History section, allowing teams to track request volume, token consumption, and overall operational activity, ensuring comprehensive oversight and management of AI interactions. This transparency assists in optimizing usage and understanding patterns over time.
API Access
Has API
API Access
Has API
Integrations
Claude Fable 5
Claude Fable 5.1
Claude Opus 4.6
Claude Sonnet 4.5
DeepSeek-V4-Pro
GLM-4.7
GLM-5.3
GPT-4.1 nano
GPT-5.2-Codex
GPT-5.4 Pro
Integrations
Claude Fable 5
Claude Fable 5.1
Claude Opus 4.6
Claude Sonnet 4.5
DeepSeek-V4-Pro
GLM-4.7
GLM-5.3
GPT-4.1 nano
GPT-5.2-Codex
GPT-5.4 Pro
Pricing Details
No price information available.
Free Trial
Free Version
Pricing Details
$0.48 per output
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Base Compute
Founded
2026
Country
Australia
Website
www.basecompute.co/getbasert
Vendor Details
Company Name
Keak
Country
United States
Website
cheaperinference.com