Search and filters
Filter by type, category, favorites and responses. Keywords are collected from your prompts automatically.
New
File attachments, chat export & usage charts
Your prompt library,
Your prompt library,
versioned, priced and ready to use.
Prompt Management Studio keeps every AI prompt you rely on in one searchable workspace. Fill placeholders in a form, compare model responses and see what each run costs. All of it stays in your browser.
- No account needed
- Runs in your browser
- Data stays on your device
1,000built-in prompts with example responses
28AI providers with free tiers to chat with
4chat export formats: Markdown, PDF, CSV, JSON
0accounts or servers holding your data
Features
Everything you need to manage prompts at scale
From the first draft to the version you run every day: one place to write, refine, price and reuse. Read the guide.
Placeholders that become a form
Mark the variable parts of a prompt and pick a field type. Generate turns them into a form and shows the finished prompt as you type, ready to copy.
-
{{tone:select[formal, friendly]}}becomes a dropdown -
{{words:number}}becomes a number input -
{{source:file}}inserts a file's text, read locally
Chat with 28 free LLM APIs
Add your key for any provider with a free tier and chat with any of its models. Replies render as Markdown, and every message shows its tokens, cost and time.
- Attach text and code files, or images for vision models
- Switch the model mid-chat; earlier replies keep theirs
- Rename and pin chats, export as Markdown, PDF, CSV or JSON
Turn a good chat into a reusable prompt
Found a message that works? Save it to your library in one click, swap the parts that change for placeholders, and keep the model's answer as a response.
- Title, category, type and keywords filled in for you
- The reply is saved as a response, priced for its model
- Placeholder syntax explained right in the form
Versions and responses, side by side
Save a new version each time you refine a prompt. Add what each model answered with the + button: paste the response, pick the model and the version it belongs to.
- Every version kept, newest first
- Responses linked to the version they answered
- Input, output and total cost per response
See usage and cost per model
A line per model shows tokens, cost or requests per day. Hover any day for exact numbers, and turn models on or off to compare the ones you care about.
- 7 days, 30 days or all time
- Token counts reported by the provider
- Per-model totals, average time and cost
Know what every prompt costs
One table lists every provider's models with their price per million tokens. Edit any price, add a model to a provider, and price the whole library with the model you use.
- Listed rates for 80+ models, editable
- Models you add show up in chat right away
- Cost per run and per 1,000 runs
Local-first and private
Prompts, chats, API keys and prices live in your browser's IndexedDB. Chat messages go only to the AI provider you pick.
Built-in library
Start with 1,000 ready-made prompts. New built-ins are added on load without overwriting your edits.
JSON import
Bring in a whole batch of prompts at once with title, category, type, keywords and text.
Copy with token count
Copy any prompt or response in one click and see how many tokens it uses before you paste it.
Export your chats
Download any chat as Markdown, CSV or JSON, or save it as a clean, print-ready PDF.
How it works
From scattered prompts to a reusable library in minutes
-
01
Collect
Start from the built-in prompts, write your own, import a batch as JSON, or save one straight from a chat.
-
02
Refine
Edit, save versions, and log the responses different models give you.
-
03
Generate
Fill in the placeholders, check the token cost, and copy the finished prompt.
FAQ
Questions, answered
Where are my prompts stored?
In your browser's IndexedDB, on your device. Prompt Management Studio has no server of its own. Only chat messages leave your browser, sent directly to the AI provider you chat with. Clearing your browser's site data removes everything.
Do I need an account?
No. Open the app and start working. There is no sign-up and no login.
How are costs calculated?
For chats, token counts come from the provider whenever it reports them. They're multiplied by each model's listed price per million tokens, which you can edit in the Models tab (set 0 for free-tier usage). Prompt costs in the library are estimated at about four characters per token.
Which AI models can I use?
The Chat tab works with 28 providers that offer free tiers through OpenAI-compatible APIs, such as Groq, Google Gemini, Mistral, OpenRouter and Z AI (see all providers). Add your own API key and pick any model they offer, and switch models mid-chat. A model that isn't listed can be added to its provider in the Models tab.
Where is my API key stored?
Only in your browser, and it is sent only to the provider it belongs to. Anyone with access to your browser profile can read it, so don't use Prompt Management Studio on a shared computer with keys you want to keep private.
Can I attach files to a chat?
Yes. Attach text and code files up to 512 KB, which every model can read, or PNG, JPEG, WebP and GIF images up to 5 MB for models that support vision. Drop them on the message box or paste images directly.
Can I export a chat?
Yes, as Markdown, CSV, JSON or PDF. JSON keeps everything, including attachments, so it works as a backup. PDF opens your browser's print dialog with a clean, print-friendly copy.
Which placeholder types are there?
Text (the default), number, file and select. Write {{name}}, {{name:number}}, {{name:file}} or {{name:select[a, b, c]}}. The placeholder reference has examples for each.
Can I import my existing prompts?
Yes. Paste a JSON array of prompts with title, category, type, keywords and text into the Add Prompt tab.
Stop losing good prompts.
Open the app and build a prompt library you'll actually reuse.
Open the app