Cline

Cline connects to Actualyze through its OpenAI Compatible provider, which speaks the Chat Completions API. You enter the base URL and your Actualyze API key, and Cline fetches the models your key can call so you can pick one from a list. Cline reads only the model IDs from that list, not their limits, so you then set the model's context window and image support yourself.

#Before you start

• An Actualyze API key with the inference scope and read-write permission. Workspace Admins, Members and FinOps Managers who belong to a team can create one: in the Actualyze app, select API Keys under ADMIN in the sidebar (every role that can hold keys sees this page, not only admins), then select Create API Key. Keep the default Read & Write permission. The key is bound to one team and one budget, and that budget is the one your Cline usage draws down.
• A model your key can call that supports tool calling. Cline reads files, runs commands and edits code through tool calls.

#Install

In VS Code and VS Code-based editors, open the Extensions view, search for Cline, and click Install. In a JetBrains IDE, open Settings → Plugins → Marketplace, search for Cline, click Install, then restart the IDE and open Cline from View → Tool Windows → Cline.

The CLI installs through npm and needs Node.js 20 or later (Cline recommends 22):

npm install -g cline

Cline's installation guide covers the other editors and the desktop app.

#Connect to Actualyze

In the editor, open Cline and click the settings (gear) icon. On the API Configuration tab, fill in the provider:

• Keep /openai/v1 at the end of the base URL. Cline appends /chat/completions itself, and /models when it fetches the model list.
• Once the base URL and key are in, Model ID turns into a list of the models your key can call. Pick one that supports tool calling.
• To use a model that isn't in the list, choose Use custom model ID… and type the ID exactly as Actualyze shows it.

#Model Configuration

The model list gives Cline only IDs. For a model it doesn't already know, Cline assumes a 128,000-token context window and image support. Click Model Configuration below the provider fields to expand it, then set Context Window Size, Max Output Tokens and Supports Images to match the model. Copy the values from the model's entry in the Actualyze Model Catalog, or ask Actualyze for them with your key:

curl -s https://app.actualyze.ai/openai/v1/models/<model-id> \
  -H "Authorization: Bearer <your-actualyze-api-key>"

A null means Actualyze has no value for that field.

The input and output price fields only feed Cline's own cost display. Actualyze meters and charges each request against the key's budget whether you fill them in or not.

#The CLI

The CLI sets the same provider in one command:

cline auth -p openai-compatible \
  -k "<your-actualyze-api-key>" \
  -m <model-id> \
  -b https://app.actualyze.ai/openai/v1

Then run cline in a project directory. The CLI stores the key in ~/.cline/data/settings/providers.json. It has no Model Configuration fields: for a model it doesn't already know, it assumes a 128,000-token context window, so pick a model whose context_window is at least that.

#Choose a model

Every model in the Model ID list is one your key can call; pick one whose capabilities.tool_use is true in the Actualyze listing. Cline uses the same model in Plan and Act mode unless you check Use different models for Plan and Act modes; then each mode keeps its own Model ID and Model Configuration.

When you pick another ID, Cline carries the Model Configuration values you set for the previous one over to it, so update them to match the new model.

An administrator can hide a catalog model from the list while leaving it callable by name. Enter that one with Use custom model ID….

#Troubleshooting

• 402: a spend limit stopped the request before any model ran, so nothing was charged. The message says which limit: usually the key's budget, or the key's own monthly limit.
• 401: the key was rejected. It may be mistyped, revoked or expired, lack the inference scope, or belong to someone who is no longer on the key's team.
• 403: the request was refused. If the message says read-write permission is required, the key is read-only; create a read-write key. Otherwise your team can't use the model you asked for; check its access in the Model Catalog or pick another.
• 402 saying Budget required: the key's budget was deleted, archived or retired, or you no longer have access to it. Create a new key bound to a budget you can use.
• The Model ID field is plain text instead of a list: Cline couldn't fetch https://app.actualyze.ai/openai/v1/models with that key. Check the base URL and key. You can still type a model ID.
• 400 once a task runs long: the conversation no longer fits the model's context window. Set Context Window Size to the model's context_window so Cline compacts the conversation before it reaches the limit.
• 404 model not found: the model ID doesn't match a catalog model or Virtual Model your workspace serves. Check for a typo or a provider/ prefix Actualyze doesn't list.
• Connection errors on every request: check the base URL. It must end in /openai/v1.
• Cline can't edit files or run commands: the model may not support tool calling. Pick one whose capabilities.tool_use is true.

#Reference

Requests you cancel mid-stream still draw down the usage they consumed.

For Cline's own settings, see the OpenAI Compatible provider guide and the CLI reference.