Docs/Workspace
Chat
How does the workspace work, and what are its limits?
Checked against the code on
The workspace is the browser side of askr: https://heyaskr.ai/chat. Sign in, pick a model, type. No key, no setup. Every model in the picker draws on the balance you funded.
How a turn works
- Pick a modelThe picker shows what one typical turn costs on each model (1,000 tokens in, 500 out), cheapest first. Switching keeps the conversation, so you can hand the same question to a second model.
- Type and sendThe reply streams in. Stop it early and you pay for what was generated, nothing after.
- See the costEach reply shows the credits it cost. The wallet lists every turn.
Limits
- Messages kept
- The last 20 are sent to the model, oldest dropped first to fit
- Message size
- 48,000 characters
- Conversation size
- 120,000 characters sent per turn; older turns fall off, the chat continues
- Reply length
- Up to 8,192 tokens per turn, thinking included; less if the balance cannot cover it
- Pace
- 20 turns per minute
- Deadline
- 4 minutes per reply
The API allows longer replies and conversations. When you outgrow the workspace, the CLI is the next step and takes a minute to set up.
What stays and what does not
A conversation exists only in the browser tab you typed it in. Close the tab and it is gone; nothing is stored on our side, and nothing you type trains a model. Images and video clips you make are different: they are kept in your library so you can get them back.
If a model refuses to answer
A reply with no content is treated as an error, not an answer, and is not charged. A model whose provider is not currently serving it says so before the turn runs. Listed but refused. Every error in the workspace ends with a code; the list says what each one means.