← Pricing & setup guides

Roo Code shut down: API pricing for Cline, ZooCode and Kilo Code instead

Roo Code shut down on May 15, 2026 and its repo is archived. Your provider setup carries over to Cline, ZooCode or Kilo Code, so compare billing and native tool support in the agent you move to.

The buying decision

Move off Roo first: it gets no fixes or new model support. Then a cheap chat endpoint is useful only if it supports the native tool calls your new agent needs. Test a file edit and its verification before comparing monthly costs.

Keep the provider, change the extension

Roo Code shut down on May 15, 2026, along with Roo Code Cloud and Roo Code Router. The Roo team recommends Cline, the extension Roo was forked from; ZooCode, a fork the Roo community started, keeps Roo's modes; Kilo Code is another maintained option. All three have an OpenAI Compatible provider that takes the same provider URL, API key and model ID Roo did, so you can switch extensions without changing your model account. Record your existing settings first so you can restore them.

Native tools are a buying requirement

Roo's documentation said native tool calling was its only supported tool protocol, and the agents that replace it lean on tool calls just as hard. A gateway returning fluent chat text has not passed that requirement. Verify that a tool request arrives with a valid name and arguments, the file operation completes, and the agent can use the result in the next turn. Check streaming behavior as well if your workflow depends on incremental tool arguments.

Set up Standard Compute in Roo's successor

Use the extension's OpenAI Compatible provider. Keep your real API key in your local client.

  1. Choose OpenAI Compatible in the provider settings of Cline, ZooCode or Kilo Code.
  2. Enter https://api.stdcmpt.com/v1 as Base URL and your Standard Compute key as API Key.
  3. Use standardcompute as the model ID.
  4. Match the context and output settings to the model behavior you have selected in the provider dashboard; do not invent token prices for a routed model.
  5. Try one small file change, inspect the diff and run its verification before moving a long task.

Compare three completed tasks

Use a bug fix, a bounded refactor and a test-writing task from the same repository revision. Include retries and failed attempts in the budget consumed. A cheaper token rate can lose its advantage when the agent requires more repair turns. Separate your monthly subscription fee from this sample's allowance consumption; three successful tasks do not establish how much a full working month will cost.

Run your own comparison

Use the same task, starting revision and acceptance check. Record every retry and failed attempt so the result reflects the work you actually paid for.

Sources and setup references