---
title: "oz0 replay reprice"
description: "Usage and flags for oz0 replay reprice."
canonical_url: "https://docs.oz0.ai/reference/cli/oz0/replay/reprice"
---
# oz0 replay reprice

> Usage and flags for oz0 replay reprice.

For: Operators and developers looking up a command.

A reprice reads every model call the gateway metered in the window (the tenant's own work: comparisons, evals and other jobs the platform runs about the agents are left out) and prices its recorded tokens again, input, output, cache reads and cache writes apart, with no model call. Give exactly one change:

--prices FILE    a price sheet: JSON {"\<provider>/\<model>" or "\<model>": {"input_mtok", "output_mtok",
"cache_read_mtok", "cache_write_mtok", "per_second"}} in dollars per million tokens
--model P/M      every call at that model's prices (the tenant's provider record, else the public price list) on
the tokens it recorded: same tokens, another price; whether that model would have done the work as
well is not measured
--cache LAYOUT   none: no prompt cache at all, what was read from it and written to it priced as input; longer and
stable-prefix: the misses the gateway put down to an expired cache, or to a changed prefix (tools or
instructions), read from the cache instead, where the server records why each miss happened

The figures are exact to the micro-dollar for each call, effective and at the list price, per agent, model and team (a team below the works-council threshold folded into "other teams"). Calls without a price for the change, without tokens, or without a recorded miss cause keep their recorded cost on both sides and are counted. The self-check prices each call again at its own model with today's prices: a price that changed since shows there, not as a difference.

No payload is read. Starting one needs governance.write and the content permission, as every replay does.

## Usage

```bash
oz0 replay reprice (--prices FILE | --model PROVIDER/MODEL | --cache none|longer|stable-prefix) [--since 7d] [flags]
```

## Flags

<table>
<thead>
  <tr>
    <th>
      Flag
    </th>
    
    <th>
      Type
    </th>
    
    <th>
      Default
    </th>
    
    <th>
      Description
    </th>
  </tr>
</thead>

<tbody>
  <tr>
    <td>
      <code>
        --agent
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      
    </td>
    
    <td>
      only this agent's jobs
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --cache
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      
    </td>
    
    <td>
      a cache layout: none, longer or stable-prefix
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --json
      </code>
    </td>
    
    <td>
      bool
    </td>
    
    <td>
      
    </td>
    
    <td>
      print JSON instead of a table
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --model
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      
    </td>
    
    <td>
      &lt;provider>/&lt;model> whose prices every call is priced at, on its own tokens
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --plugin
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      
    </td>
    
    <td>
      only the jobs of this plugin's agents
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --poll
      </code>
    </td>
    
    <td>
      duration
    </td>
    
    <td>
      <code>
        2s
      </code>
    </td>
    
    <td>
      with --wait, how often to look
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --prices
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      
    </td>
    
    <td>
      a price sheet (JSON) to price every call with
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --since
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      <code>
        7d
      </code>
    </td>
    
    <td>
      how far back to read: 7d, 36h, 90m
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --tenant
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      <code>
        default
      </code>
    </td>
    
    <td>
      tenant
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --wait
      </code>
    </td>
    
    <td>
      bool
    </td>
    
    <td>
      
    </td>
    
    <td>
      wait for the report and print it
    </td>
  </tr>
</tbody>
</table>

## Inherited flags

<table>
<thead>
  <tr>
    <th>
      Flag
    </th>
    
    <th>
      Type
    </th>
    
    <th>
      Default
    </th>
    
    <th>
      Description
    </th>
  </tr>
</thead>

<tbody>
  <tr>
    <td>
      <code>
        --context
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      <code>
        $OZ0_CONTEXT or &lt;config dir>/orchestrator-zero/context.json
      </code>
    </td>
    
    <td>
      CLI context file written by server init
    </td>
  </tr>
  
  <tr>
    <td>
      <code>
        --log-level
      </code>
    </td>
    
    <td>
      string
    </td>
    
    <td>
      <code>
        info
      </code>
    </td>
    
    <td>
      log level: debug, info, warn or error
    </td>
  </tr>
</tbody>
</table>

See [all `oz0` commands](https://docs.oz0.ai/reference/cli/oz0) and the [global flags](https://docs.oz0.ai/reference/cli/oz0#global-flags).


## Sitemap

See the full [sitemap](https://docs.oz0.ai/sitemap.md) for all pages.