Core AI Models vs ModelHub API

Core AI Models and ModelHub API are both inference engines & infra tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Core AI Models

The repository ships three concrete layers: Python export recipes for popular Hugging Face models, reusable PyTorch primitives for authoring custom models in Core AI format, and a Swift package that slots those exported models into macOS and iOS apps. The CLI tooling lets you run models directly on a Mac before touching Xcode. Where the workflow breaks is at the edges of what the export recipes cover — models outside the supported Hugging Face roster require you to author your own export logic using the Python primitives, which assumes familiarity with both PyTorch internals and Core AI's model format. The skills directory adds coding-agent plugins, but the core offering is an export-and-runtime pipeline, not an autonomous agent loop.

ModelHub API

ModelHub is a hosted API gateway that puts 45 Chinese and global LLMs — DeepSeek V4, Qwen 3, GLM-4, Doubao, Kimi — behind a single OpenAI-compatible endpoint. You swap your base_url, keep your existing SDK, and your token bill drops. The vendor states prompts are never stored and payments run through Paddle under PCI Level 1 certification. The ceiling appears fast: no self-hosted option, no agentic tooling, no fine-tuning surface. Teams that need dedicated infrastructure or low-latency SLAs will exhaust what the service offers and contact the Enterprise tier — or leave.

Attribute	Core AI Models	ModelHub API
Pricing	Free	Paid
Price	—	$15/month
Free trial	No	No
Open source	Yes	No
Has API	No	Yes
Self-hosted option	Yes	No
Platforms	macOS, iOS	Web, CLI, API, OpenAI-compatible SDK
Pros	Export recipes for popular Hugging Face models are included out of the box, so you skip the format-guessing phase that typically consumes the first day of any on-device ML project. The Swift runtime package is built directly on Core AI framework and lives in the same repo as the export tooling, which means the Python-to-Swift handoff follows a maintained path rather than an improvised one. Reusable PyTorch primitives for custom model authoring give you a structured starting point when your architecture is not covered by the existing recipes, rather than a blank canvas. CLI tooling for local Mac inference lets you validate model behavior before opening Xcode, catching export problems before they become app-integration problems. BSD-3-Clause license and a fully public GitHub repository mean you can fork, audit, and modify the export logic — critical when Apple silicon deployment has compliance or reproducibility requirements.	OpenAI SDK compatibility via a base_url swap, so existing codebases require no refactoring and teams avoid the integration cost of adopting a net-new client library. Per-token pricing on DeepSeek V4 Flash starting at $0.15/M tokens, which means high-volume workloads — batch summarization, large-scale code generation — that would exhaust an OpenAI budget stay economically viable. No Chinese phone number or regional payment method required, so international developers who hit identity-verification blocks on direct Chinese model APIs can provision access in minutes. Prompts are never stored and never used for model training, according to the vendor, so teams with baseline data-handling policies avoid the contractual exposure that comes with providers who retain inference data. 45 models behind one key, so switching from DeepSeek to Qwen or Doubao for a specific task is a model-name change in the request body — not a new vendor contract, new SDK, or new auth flow.
Cons	Models outside the supported Hugging Face export recipes require writing custom export logic with the Python primitives; this is not a guided path, and teams without PyTorch internals experience stall here and move to ONNX-based pipelines with broader model coverage. There is no API and no hosted runtime — everything runs from a locally cloned repository, so teams expecting a managed service or cloud-side inference endpoint abandon this and use a hosted inference provider instead. The tool produces Core AI format artifacts, which are not portable outside the Apple ecosystem; any project that also targets Android or web inference requires a parallel export pipeline, meaning two separate toolchains to maintain.	No self-hosted or on-premise deployment option exists. Teams under data-residency mandates that prohibit routing prompts through third-party cloud infrastructure cannot use ModelHub at all — those teams go directly to self-hostable model weights via Ollama or a private cloud deployment. The service provides chat completion inference only, with no built-in tool-use framework or agent runtime. Teams building multi-step agents that branch based on tool output must wire a separate orchestration layer — LangChain, LlamaIndex, or equivalent — on top of ModelHub, meaning they are maintaining two systems from the first agent they ship. Latency is shared-infrastructure latency with no published p99 SLA outside the Enterprise tier. Production applications where response time is a user-experience constraint — real-time voice, interactive copilots — will hit unpredictable queuing during demand spikes and have no contractual recourse short of negotiating an Enterprise deal. The full model catalog and multiple API keys are gated behind paid tiers; the free credit covers evaluation only. Teams that prototype on free credit and then need concurrent key distribution for a multi-service architecture face a hard paywall before they finish scoping the project.

Bottom line

Core AI Models is free while ModelHub API is paid; Core AI Models is open source; only ModelHub API exposes a public API. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Core AI Models and ModelHub API?

Core AI Models is Free and open source, while ModelHub API is Paid. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Core AI Models better than ModelHub API?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.