Back to docs
    Skip to content

    Liro

    Team plan

    • Overview
    • Inbox3
    • Documents
    • Agents
    • Analytics
    • Settings
    1. Liro
    2. Settings
    3. Model policy
    Model policy
    • You
    • Workspace

    Model policy

    Which model does each kind of work, what to try when it fails, and how much Liro may spend.

    $209 in the last 30 days

    Your last 30 days

    Change anything below and this shows what it would have cost.

    Cost

    $209

    Chat reply starts in

    0.6 s

    $500 cap reached on

    Never

    Model for each kind of work

    Pick per task. Prices are for the last 30 days of that task alone.

    • Chat

      Answers in the assistant

      $41
    • Summaries

      Documents and threads

      $20
    • Code

      Agents that write or fix code

      $146
    • Search index

      Making documents searchable

      $2

    When a model fails or is busy

    Tried in this order. The first one that can do the task answers, and the run notes which one it was.

    1. 1

      Swift 3

      Fast and cheap · starts in 0.6 s

    2. 2

      Deep 3

      Careful reasoning · starts in 2.1 s

    3. 3

      Craft 1

      Tuned for code · starts in 1.3 s

    Spend caps

    Counted from the 1st of each month. Admins are told at 80%.

    $

    When it's reached

    Work carries on, on Swift 3, until the month resets.

    Each person, per month

    One busy agent can't use the whole workspace's budget.