Integrations

Use FullsendAI with Cursor

Cursor lets you override its OpenAI base URL and add your own model names, so its chat and agent can run on FullsendAI models.

Set it up#

Create a key on API keys. Don't lock it to IP addresses: Cursor sends these requests from its own servers.
In Cursor, open Settings → Models, find API Keys, paste the key into OpenAI API Key, switch on Override OpenAI Base URL and enter https://fullsendai.com/v1.
Click Add model and add each FullsendAI model ID you want, like deepseek-v4.1-flash. Turn off the built-in models you don't want sent to FullsendAI.
Pick the model in the chat or agent panel and send a message. It appears in Logs within a second.

Model ID	Use it for	Price / 1M in / out
`nef-4.0`	Security research: code review, exploit analysis, CTFs and pentest tooling.	$0.60 / $2.40

Use the model picker under the chat box. Every model ID you added is listed there; add more under Settings → Models at any time.

Tab completion always runs on Cursor's own models; chat and agent requests go to FullsendAI.
Some Cursor features need a Cursor plan whatever key you use. Cursor decides which ones; check its own docs.

Symptom	Fix
“Invalid API key” when verifying	Check the key, and that the base URL ends in `/v1` with no trailing path.
`403 ip_not_allowed`	Remove the key's IP lock: Cursor's servers make the call, not your machine.
`404 model_not_found`	A built-in model name was sent to FullsendAI. Turn it off, or add the FullsendAI model ID instead.
`402 insufficient_quota`	Add credit or turn on auto top-up.