LLMAPI 1.2.0

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: [link removed]
Privacy Policy: [link removed]
Support: support@freellmapi.co