Cursor with FluxCDN AI
Cursor lets you change the OpenAI address and add your own models. That works for chat in Ask and Plan modes. Agent mode isn't reliable with a custom address, and Tab completion always uses Cursor's own models. For an agent, install Cline or Kilo Code inside Cursor (VS Code guide), or run Claude Code or Codex in Cursor's terminal.
- Licence:
- Proprietary; by the available guides, custom models need a paid Cursor plan
- Platforms:
- macOS, Linux, Windows
- Address (OpenAI-compatible):
https://ai.fluxcdn.cloud/api/v1
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.
Set it up
Step 1: Clear old variables
If
OPENAI_API_KEYorOPENAI_BASE_URLare set on your system, remove them; they can clash with Cursor's setting.Step 2: Enter the key and the address
Cursor Settings → Models, then the API Keys section. Put the key in OpenAI API Key and turn it on. Turn on Override OpenAI Base URL and replace the default address with
https://ai.fluxcdn.cloud/api/v1, without/chat/completions.Step 3: Add the model
Press + Add Custom Model, enter the id exactly and turn it on.
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.+ Add Custom Modelanthropic/claude-sonnet-5.5Step 4: Chat in Ask mode
In the chat panel choose Ask mode and pick the model.
Check it works
Step 1: Ask a question
Ask about a file in Ask mode. You'll see the request under Activity in the console.
Troubleshooting
- Agent mode fails (for example “model is required” or a tools error)
- Cursor's Agent mode sends requests this route doesn't fit when the address is custom. Use Ask or Plan, or use Cline, Kilo Code, Claude Code or Codex inside Cursor.
- Answers come back empty
- Set Settings → Network → HTTP Compatibility Mode to HTTP/1.1.
- “does not work with your current plan or api key”
- Custom models aren't available on Cursor's free plan, or the key wasn't copied right.
- Cursor's own GPT models stop working
- Cursor's OpenAI address override applies to every OpenAI model. Turn it off to use Cursor's own models.
- 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. - 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”.
Limits
- Requests are sent from Cursor's servers, not your computer, so Cursor sees the key and the requests. Cursor's Zero Data Retention policy doesn't apply to requests made with your own key.
- Tab completion never uses your key, and Agent mode isn't reliable.

