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
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.
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.
Price per million tokens. Free plan prices, in Toman at today's rate. Routers (
router/autoand the like) are not recommended for agents: an agent needs a model that is sure to support tools.Providers & API keys · Models AssignmentURL: 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
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 runjunie --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
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, notclaude-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/v1and add the rest themselves; don't write/chat/completionstwice 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_exceededorbudget_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.

