Skip to content
FluxCDNFluxCDN
esc
On this page

DocsTools guide

JetBrains IDEs with FluxCDN AI

AI Assistant in the JetBrains IDEs takes an “OpenAI-compatible” provider, with no JetBrains AI subscription. The key stays on your computer. Claude Code, Cline and Continue have JetBrains plugins too.

Licence:
Proprietary; the AI Assistant plugin is free
Platforms:
macOS, Linux, Windows
Address (OpenAI-compatible):
https://ai.fluxcdn.cloud/api/v1
Address (Full request address):
https://ai.fluxcdn.cloud/api/v1/chat/completions

Before you start

  • Create an API key. On the API keys page press “Create key” and copy the key right away. It starts with flux_live_ and is never shown in full again.
  • Give agents a key of their own and set a daily or monthly spending limit on it with “Limits”. Agents send request after request by themselves; the limit stops spending you didn't expect.
  • Have some credit in the account (Billing).
  • In the examples, put your own key where it says flux_live_YOUR_KEY.

AI Assistant

  1. Step 1: Add the provider

    Settings → Tools → AI Assistant → Providers & API keys, section Third-party AI providers: choose OpenAI-compatible, enter the address and key, turn on Tool calling (agents need it), then press Test Connection and Apply.

  2. Step 2: Assign the models to features

    Custom models aren't assigned to features by themselves. On the same page, under Models Assignment, give Core features the main model and Instant helpers a quick one.

    Pick a setup; the settings below change with it. Any id from the models page works in their place too.

    Price per million tokens. Free plan prices, in Toman at today's rate. Routers (router/auto and the like) are not recommended for agents: an agent needs a model that is sure to support tools.

    Providers & API keys · Models Assignment
    URL:              https://ai.fluxcdn.cloud/api/v1
    API Key:          flux_live_YOUR_KEY
    Core features:    anthropic/claude-sonnet-5.5
    Instant helpers:  anthropic/claude-haiku-5.5

Junie CLI

  1. Step 1: Create a model profile

    Junie adds nothing to the address, so give the full request address. Put the key in FLUXCDN_API_KEY; if it isn't set, the profile doesn't load. Then run junie --model custom:fluxcdn, or choose it in the Custom tab of /model.

    ~/.junie/models/fluxcdn.json
    {
      "baseUrl": "https://ai.fluxcdn.cloud/api/v1/chat/completions",
      "id": "anthropic/claude-sonnet-5.5",
      "apiType": "OpenAICompletion",
      "apiKey": "${FLUXCDN_API_KEY}",
      "displayName": "FluxCDN Claude Sonnet 5.5",
      "fasterModel": { "id": "anthropic/claude-haiku-5.5" }
    }

Check it works

  1. Step 1: Test the connection

    Test Connection in the settings, then the AI Chat window: the provider's models have their own section in the model list. Ask a question.

Troubleshooting

Features still use JetBrains' models
Assign the models under Models Assignment (step 2).
Error 401 or invalid_api_key
The key wasn't copied whole, was revoked, or went in the wrong field. It starts with flux_live_ and has no spaces. If the tool reads it from an environment variable, open a new terminal or window after setting it.
Error 402, insufficient_credit (in Codex: insufficient_quota) although you have credit
Before each request, the most it could cost is set aside from your credit. When the answer ends, only the real cost is taken and the rest is released. A tool that asks for a very long output on every request sets aside a large amount. Lower the tool's output limit (for example to 32000 tokens) or add credit.
Error 404 or model_not_found
The model id must be exactly as on the models page, with the maker's prefix: anthropic/claude-sonnet-5.5, not claude-sonnet-5.5. Lower case and dots matter. Copy the id rather than typing it.
A 404 that doesn't mention the model
The base address is wrong. Most tools want https://ai.fluxcdn.cloud/api/v1 and add the rest themselves; don't write /chat/completions twice and don't leave out /v1. See the which address table.
The agent calls no tools, or the model is missing from the agent's list
Pick a model that supports tools; it has the Tools label on the models page. Some tools need that switched on for the model (the steps above). Routers are not recommended for agents.
Error 429: rate_limit_exceeded or budget_exceeded
Either requests per minute went over the limit (wait a little; most tools retry by themselves), or this key's spending today or this month reached its limit. See it on API keys under “Limits”.
Error 502, 503, 504 or 529
The model's service was briefly unavailable. Send again; most tools do it themselves. A request that fails before answering costs nothing. If it lasts, switch to another model for a while.

Limits

  • Inline completion and next-edit suggestions don't use these models. JetBrains says not every feature is guaranteed with other providers' models.
  • AI Assistant takes only an OpenAI-compatible address, not an Anthropic one.

What doesn't work this way →