← All integrations

OpenAI-compatible · Custom base URL · Terminal coding agent

Use Standard Compute with Junie CLI

JetBrains' coding agent for the terminal, with custom model profiles defined as JSON files. Paste three settings into Junie: the base URL, your Standard Compute API key and the model.

JetBrains' docs say bring-your-own-key use needs no JetBrains AI subscription: the provider bills the usage. A profile can also set a fasterModel for helper tasks, such as z-ai/glm-5.3-flash.

Eligible new accounts can try $0.25 of compute, with no card. See trial terms →

Your connection settings

Copy these values, then put them where Junie expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in Junie

  1. Create ~/.junie/models/standardcompute.json. The file name becomes the profile ID.
  2. Set baseUrl to https://api.stdcmpt.com/v1/chat/completions, id to standardcompute, apiType to OpenAICompletion and apiKey to "${STANDARDCOMPUTE_API_KEY}".
  3. Export STANDARDCOMPUTE_API_KEY and run junie --model custom:standardcompute, or pick it under the Custom tab of the model selector.

Junie docs ↗

What changes in Junie

Billing
Junie requests draw on one monthly compute budget, with plans from $19 a month. There is no per-token bill. When the budget is used, requests stop until renewal or an upgrade, unless you turn on pay as you go.
Models
The model standardcompute picks a frontier or an efficient model for each request. An exact model ID from the Models page pins one model instead.
Good to know
Junie uses baseUrl as the complete endpoint and appends nothing, so a URL that stops at /v1 returns a 404. If a referenced ${VAR} is not set, the profile does not load. These profiles are a Junie CLI feature.

Read next