Understand tokens and model rates
Learn what input, cached input, and output mean before choosing a plan.
What you send and what you receive
Input tokens represent the content you send to a model, including prompts and conversation context. Output tokens represent what the model returns. Tokens are pieces of text, so a token is not always a whole word.
Read the model table
Model rates are listed in US dollars per one million tokens. Input, cached input, and output have separate prices. Cached pricing applies when the service supports reusing input; it is not a discount on every request.
Estimate a request
Multiply each token count by its listed rate and divide by one million. Add the input and output costs. For eligible cached input, use the cached rate for those tokens rather than counting them again at the regular input rate. Actual usage depends on the prompt, conversation history, and response length.
Compare plans separately
The monthly or 30-day price on a plan card is not a per-million-token rate. Confirm the included allowance, models, and account limits before activation. A higher plan price alone does not tell you how many requests it includes.
Pick for the work you do
Consider the cost of the context you send as well as the answer you expect. Check which models are available to your account before configuring an app. Compare plans or set up your access.
Talk to the team
Open Palepale Discord for activation, device credentials, and account support. For app setup, copy a connection example. For payment or renewal questions, read plans and billing.
Need a hand?
Open Palepale Discord for activation or account support. Compare API offers or choose a plan.