MLXHub vs LLMAPI

An AI that lives on your iPhone and iPad, even without internet. Talk to it and hear it answer out loud, create images right on your device, and turn it into a server for your local network. No message counter. Talk to it. It talks back. Voice mode transcribes what you say on your device, in the languages you have set up, answers with a natural voice and lets you cut in whenever you want. An assistant that can help you act Ask about your calendar, reminders, Health data, photos or music library with supported tools; you choose which ones to authorize. With MLXHub Plus, create events and reminders, log Health data and save reusable instructions as Skills. Tools and results depend on the model you choose. Memory you control Keep what is worth remembering for future chats, and review, pin or delete it in Settings. With Plus, compatible models can also save or remove memories on their own. Create images on your device Download a compatible image model and generate images without uploading anything to the cloud, from the Image tab or by asking in a chat. Pause an image and resume it later. Free up to 512 px; up to 1280 px with Plus. Bigger open models Download open-weight language and vision models. Supported MoE models load their experts from storage when needed, which is how a 35B MoE runs on iPhone 17 Pro Max and on supported iPads. Capacity and performance depend on your device, model and context. Text, photos and documents Write, attach a photo or a document and ask a compatible model for help, with the personality and instructions you set. On devices with Apple Intelligence you can also use Apple's on-device model. Measure your device The benchmark scores the speed of your iPhone or iPad with real models. Publish your result to the leaderboard and compare it with other devices. Your devices, working together Connect compatible devices on your local network to run models across them. Joining a mesh is free; hosting one requires MLXHub Plus. A local server for your apps Serve chat and embeddings to apps and scripts on your local network through a standard chat completions API (/v1/chat/completions, /v1/embeddings), with authentication and local discovery. It includes a web chat portal for any browser on your Wi-Fi and a voice center to talk to the server's model. Unlock the server with a one-time purchase or with MLXHub Plus; it runs while the app is in the foreground. All yours, unmetered No token limits, no message caps, no monthly quota, and no AI company keeping an eye on what you write. Inference happens inside your device, and your conversations are not uploaded to any cloud AI service: an assistant and a server you can use without limits, under your control. And if you would rather not subscribe, the one-time Lifetime purchase gives you unlimited inference for life and every feature that lands later, at no extra cost. Because this keeps getting better: with every update, every week with each new open-weight model and every year with each new device and iOS release from Apple. Privacy and connections Downloaded models can work offline. Features you enable, such as web tools, the LAN server and mesh, communicate with their services or devices. No ads or required MLXHub account. Anonymous product analytics and diagnostics can be turned off in Settings. See our Privacy Policy. Requires an iPhone or iPad with an A14 or M1 chip or later. Available models depend on your device's memory. Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Every free LLM. One app. LLMAPI is a chat client and an API router. It knows which models the big providers give away, how much quota each one has left, and which one is smartest for what you just asked — and it picks for you, on the device, in the moment. AUTO-ROUTING THAT ACTUALLY ROUTES Ask a question. LLMAPI scores every model you can reach right now — by capability, by remaining quota, by how fast it has been answering — and sends your prompt to the best one. If that provider is rate-limited, it fails over to the next one mid-request. Every answer shows what served it: provider, model, latency, and how many failovers it took. Nothing is hidden behind a spinner. Prefer to drive? Priority mode lets you drag the model chain into your own order, or pull models out of routing entirely. WORKS WITH ZERO SETUP No account. No sign-up. No credit card. Four providers serve anonymous free tiers, so the app answers your first message seconds after you open it, before you configure anything. BRING YOUR OWN FREE KEYS Every provider in the list has a genuinely free tier: Google AI Studio, Groq, Cerebras, NVIDIA NIM, Mistral, OpenRouter, Cloudflare Workers AI, Cohere, Ollama Cloud, HuggingFace, GitHub Models and more. Paste a key and LLMAPI validates it live before saving, watches its health, and round-robins across multiple keys for one provider. Keys are stored in the iOS Keychain. They go to that provider and nowhere else — not to us, not through any server of ours. You can also point it at your own local or hosted endpoint — llama.cpp, LM Studio, vLLM, any /v1 base URL. YOUR PHONE AS AN API SERVER (PREMIUM) Turn on the LAN server and your iPhone serves a standard chat-completions API to everything else on your Wi-Fi. Point any chat-completions SDK, the Anthropic SDK, curl, or any agent framework at your phone's address; it auto-routes across every free tier you can reach, exactly like the chat tab. - POST /v1/chat/completions, streaming and non-streaming - POST /v1/messages, Anthropic-compatible - GET /v1/models - Bearer-key authenticated, generated on device - Scan the QR code for a connection page with copy-paste snippets It runs only while the app is open and switched on. A Low Power Screen dims the display to near-black so an OLED draws almost nothing while serving, and a battery guard stops the server at 10% unless you are plugged in. A CATALOG YOU CAN TRUST Hundreds of models across 28 providers, with real rate limits, context windows, tool and vision support. The catalog is fetched from our service and its Ed25519 signature is verified on your device before any model loads. A tampered catalog is rejected. PRIVACY, PLAINLY - Chat history lives in a database on this phone. It is never uploaded. - Provider keys live in the Keychain. They go to the provider, and nowhere else. - There is no analytics SDK in this app. None. - No account to create, so no profile to build. - Your prompts go to the AI provider that answers them, under that provider's terms. That is the only place they go. FREE VS PREMIUM Free, forever: auto-routing, failover, quota tracking, chat history, and the anonymous free-tier models. No trial, no countdown. Premium adds: every model in the catalog rather than the keyless few, the LAN API server, and the live catalog feed — new free models and quota changes reach you the day we ship them instead of thirty days later. Premium Annual is an auto-renewing subscription. Premium Lifetime is a single payment. A NOTE ON AI OUTPUT LLMAPI relays answers from third-party models, including open community models that apply little or no filtering. Output can be wrong, biased, or offensive, and it is not reviewed by us before you see it. Long-press any answer to report it. Do not rely on it for medical, legal, or financial decisions. Terms of Use: https://freellmapi.co/terms Privacy Policy: https://freellmapi.co/privacy Support: support@freellmapi.co