Built around the full arc of how serious work gets done — from raw research to collaborative delivery. No feature bloat, just the tools that matter.
@mention any model in any message. Route one prompt to many models and compare outputs side by side in real time.
Optimizes memory, summaries, recent conversation, and token budgets before inference so models receive cleaner context.
Switch between Code, Research, Writing, Analysis, Think, and General — each tuned with a precision prompt layer for optimal results.
Upload images, PDFs, CSVs, and code files. Project-level asset libraries make files available across every session.
Multiple models collaborate on a single thread, building on each other's responses until the best answer surfaces.
Toggle live web search when prompts need current information. Meridian retrieves, cites, and synthesizes in context.
Dedicated image models available directly in the workspace. Generate, refine, and export without switching tools.
Bring your own keys for OpenRouter, OpenAI, Anthropic and custom providers — all encrypted at rest.
Token counts, image generation, and cost estimates by model and project. Know exactly what your work costs.
Top-up store with geo-aware pricing fallback. Upgrade, manage limits, and pay seamlessly through Stripe.
Full user account system with email/password, Google OAuth, Apple OAuth, demo login, password reset, and session validation — all included from day one.
Email/password, Google OAuth, Apple OAuth, and demo login. Users choose how they sign in.
Automatic session validation, refresh tokens, and secure logout across all devices.
Default model, thought trace, streaming behavior, security preferences, and account controls.
Generated code appears in a side workspace panel. Edit, iterate, and export without losing context.
Every action in Meridian is one keystroke away. Type / in any chat input to trigger commands — no menus, no clicks.
| Command | What it does |
|---|---|
/help | Open slash command list modal |
/shortcuts /keys /keyboard | Open keyboard shortcuts modal |
/new /clear | Start a fresh chat |
/stop | Abort all active streams |
/regen /retry | Regenerate the last response |
/model <name> | Fuzzy-match and pin a model |
/everyone /all | Fan-out to all workspace models |
/effort <low|med|high|max> | Set reasoning effort level |
/think | Toggle extended thinking mode |
/web | Toggle live web search |
/image | Toggle image generation tool |
/human | Toggle humanise tool |
/translate <lang> | Set target language for translation |
/bullets /numbered /table /code | Set output format type |
/attach /upload /file | Open file picker |
/compress /summarize | Compress current context |
/upgrade /pro /plan | Open upgrade modal |
Start with the free tier. Every capability is available — only limits and model access differ by plan.