daoco uses two token types to meter usage: basic tokens and premium tokens. Each covers a different category of work. Starter Trial credits and paid Starter credits reset monthly. Trial work uses the same token rules as paid Starter, but with the trial’s monthly token amounts.Documentation Index
Fetch the complete documentation index at: https://docs.daoco.org/llms.txt
Use this file to discover all available pages before exploring further.
Basic tokens
Basic tokens power chat and content generation.- A new thread starts with a base charge of 1 basic token.
- As the conversation grows, roughly every 50,000 total model tokens in that thread adds another 1 basic token.
- Longer threads with more back-and-forth will use more basic tokens over time.
Context limit
Each thread has a context limit shown as a circular meter in the chat. As your conversation grows, the circle fills up. When the context limit is reached, daoco automatically compacts older messages into a summary so the thread can continue without losing key context. You do not need to start a new thread when the meter fills up — compaction handles it for you. Starting fresh threads is still useful when switching topics, and shorter threads are more token-efficient since longer threads consume more tokens per message. See Context management for details on how compaction works and what the status indicators mean. Actions that use basic tokens: chat messages, content drafts, brand summaries, post generation, SEO help, campaign planning, and research subagents.Research subagents
When your chat triggers web research or connected account analysis, the assistant launches a research subagent. Each subagent adds to your basic token usage:- 1 basic token base charge per subagent launch.
- 1 additional basic token for every ~50,000 model tokens the subagent consumes.
Premium tokens
Premium tokens power asset and advanced generation.- Standard asset generation uses 1 premium token.
- 4K asset generation uses 2 premium tokens.
- Logo generation includes 20 free generations per organization. After that, each logo uses 1 premium token.
- Video clipping uses premium tokens when rendered clips are produced.
Video clipping
Video clipping is charged when rendered clip deliverables are created. The first rendered clip from a source video costs:| Source video length | First rendered clip cost |
|---|---|
| Up to 1 hour | 2 premium tokens |
| Over 1 hour and up to 2 hours | 3 premium tokens |
| Over 2 hours and up to 3 hours | 4 premium tokens |
A plain balanced
/clip request aims to produce 3 ready clips. For a source video up to 1 hour, that usually means 2 premium tokens for the first ready clip plus 1 premium token for each additional ready clip.Reading the usage dashboard
Open Organization > Billing to see your usage meters. Each token type shows:- Used / Included — how many tokens you have consumed out of your monthly allocation.
- Progress bar — fills from left to right as you use tokens.
- Remaining count — how many tokens are left this period.
Usage states
| State | What it means |
|---|---|
| Normal | Usage is within your included quota. |
| Limit reached | You have used all included tokens. Buy a top-up or wait for the next billing cycle. |
| In overage | Usage has exceeded your included quota and overage charges may apply. |
What happens when you hit a limit
- Chat and generation actions that require the exhausted token type will be paused.
- You will see a message asking you to manage your billing to continue.
- Buy an add-on top-up from Organization > Billing to resume immediately.
- Included tokens reset at the start of each billing cycle.