LLM Terminal

Chat with LLMs like Ollama and LM Studio or connect to cloud AI.

LLMTerminal lets you connect to cloud AI and Local Language Models through OpenAI, Anthropic, Google Gemini, Ollama, LM Studio, OpenRouter, Azure OpenAI, Mistral, Groq, Cohere, Perplexity, and other compatible providers.

Use LLM Terminal for AI chat, voice chat, image analysis, prompt engineering, AI agents, and local or cloud model access on Android.

~ K E Y - F E A T U R E S ~

> Universal AI Model Support:
Connect to GPT-4o, GPT-4, GPT-3.5, Claude 3.5, Claude 3 Opus, Gemini, Ollama, LM Studio, OpenRouter, Azure OpenAI, Mistral, Groq, Cohere, Perplexity, and more. Automatic provider detection makes setup easier.

> Streaming AI Chat:
Get real-time AI responses with token-by-token streaming. Supports Markdown, code syntax highlighting, and LaTeX math rendering. Adjust temperature and max tokens per conversation.

> Vision AI / Image Analysis:
Upload images from your camera or gallery and ask vision-capable AI models to analyze them. Works with both local and cloud models. Send multiple images in one message.

> Voice Input and Text-to-Speech:
Use voice input for hands-free AI conversations. Listen to AI responses with offline text-to-speech and replay the last response with the /repeat command.

> AI Agent Mode:
Let AI perform tasks on your device with tools for file operations, directory management, web access, shell commands, and code analysis. Safety features include safe mode and confirmation for sensitive actions.

> Prompt Library:
Use built-in system prompts like General Assistant, Python Expert, Code Reviewer, ELI5, Professional Writer, Technical Writer, Math Tutor, Creative Writer, Skeptical Analyst, and Concise Responder. Create and organize custom prompts by category.

> Prompt Variables:
Insert dynamic content before sending, including date, time, clipboard, last_message, model, device, and more.

> Image Generation:
Generate images with Stable Diffusion-compatible APIs. Configure steps and dimensions up to 2048x2048. Works with Automatic1111, ComfyUI, and similar backends.

> Usage Analytics:
Track token usage per conversation with live counters during streaming. View cost estimates based on model pricing and monitor total usage in a global dashboard.

> Export and Sharing:
Export conversations to Markdown, plain text, or PDF. Share directly through the Android share sheet.

~ G E T T I N G - S T A R T E D ~

1. Install the app on your Android device.
2. Enter your API server URL, such as a local Ollama endpoint.
3. Select your model and add an API key for cloud providers.
4. Start chatting with AI. No account is required for self-hosted models.

---

Privacy Policy:
https://llmterminal.1ndev.com/privacy-policy.html