Sleek BYOK vs Sencha

Sleek is a native iOS client for OpenRouter — bring your own key and get every major AI model in one clean, fast, beautifully minimal app. No Sleek account. No middleman servers. Your OpenRouter key stays on your device, and every request goes straight from your iPhone to the model. You pay OpenRouter's raw per-token rates for AI usage — no markup from us, ever. One app. Every modality. • Chat with hundreds of models — Claude, GPT, Gemini, Llama, and more — and switch between them in a tap. • Generate images with the latest image models, right in the conversation. • Generate video from a prompt and save it straight to Photos. • Talk hands-free with live push-to-talk voice — speak, get a spoken reply back. • Dictate into any chat with universal on-device audio capture. • Make music and download the track. Built to feel high-end. A dark, distraction-free interface with smooth streaming, clean markdown, and thoughtful micro-interactions throughout. It looks and feels like a flagship app — because it is one. Make it yours. • Presets — save reusable system prompts and parameters for different jobs. • Per-modality prompts — steer image style, voice delivery, music genre, and more independently. • Memories & folders — keep context organized and let the app pull in what's relevant. • Model explorer — browse full stats, pricing, and context windows for every model, and set defaults per task. • Fine control — temperature, max tokens, provider routing, and more when you want it; sensible defaults when you don't. Private by design. Sleek has no backend of its own. There's no analytics pipeline, no Sleek account, and no server that ever sees your conversations or your key. Everything lives on your device. What you need to get started: Sleek runs on your own OpenRouter API key (free to create at openrouter.ai). Two ways in: • Connect OpenRouter — sign in once and Sleek provisions a key automatically. No copy-pasting. • Paste a key — already have an OpenRouter API key? Add it in Settings, no account needed. Minimal on the outside. Every model on the inside. That's Sleek.

A native LLM client for on-device inference, LLM APIs, and self-hosted servers, built around a minimal, responsive interface. Download a supported model and chat offline without an API key or account. Or connect OpenRouter, direct providers, and compatible endpoints using your own credentials. On-Device Models • Download models from the built-in catalog, including Gemma 4, Qwen 3.5, Bonsai, and LFM 2.5 • Choose model sizes and quantization options to suit your device • Configure context window, reply length, and image detail where supported • Use streaming, thinking traces, image attachments, and web tools with compatible models • Reduce reprocessing of earlier messages with on-disk prompt caching Model capabilities and performance depend on the selected model and available device memory. Connections and Models • Connect OpenRouter, OpenCode, and direct providers • Add OpenAI- or Anthropic-compatible endpoints, including self-hosted runtimes such as Ollama and LM Studio • Use Chat Completions, Responses API, or Messages API • Choose an on-device or connected model per chat • Browse model catalogs and inspect context size, output limits, pricing, and capabilities where available • Configure reasoning effort, prompt caching, routing, and model tools where supported Web Search and Fetch • Use the included free web search via Markdown.new • Or configure Brave Search, Tavily, Exa, Serper, SerpApi, Parallel, or Keenable • Choose search-depth presets for Exa and Tavily • Fetch pages on device or through Markdown.new or Firecrawl • Configure fetch providers and fallbacks independently Files and Output • Attach photos, documents, and PDFs • Send PDFs natively, extract embedded text, run on-device OCR, or render pages as images • Read responses with formatted Markdown, code, mathematical formulas, and tables • Copy generated tables as a table, Markdown, or a complete image Voice Input • Use Apple Speech for on-device dictation • Download local transcription models • Connect API-based transcription providers The app is free, with no ads or app subscription. On-device models require no provider account or API key. Connected services are subject to their own pricing, limits, and data policies.