Skip to main content
Cursor is an AI-powered code editor built on VS Code. It features an agent mode for autonomous coding, tab completions, inline edits, a CLI, and cloud agents. By routing Cursor through Requesty, you get access to 300+ models through a single API key, automatic provider failover, and centralized usage tracking. Using the Requesty integration, you can:
  • Access 300+ models from OpenAI, Anthropic, Google, Mistral, and many other providers through one API key.
  • Track and manage your spend in a single location.
  • Apply fallback policies, load balancing, and latency routing to keep Cursor responsive.

​
Quick Start

Cursor supports Requesty through its Override OpenAI Base URL feature. Requests from Cursor’s OpenAI provider are routed through Requesty, so you can use any model from the Model Library.

​
1. Get your Requesty API key

  1. Sign up or log in at Requesty
  2. Navigate to the API Keys page
  3. Create a new API key
  4. Copy your key (starts with rqsty-sk-...)

​
2. Configure Cursor

  1. Open Cursor Settings (gear icon or Cmd/Ctrl + ,)
  2. Navigate to Models, then expand the API Keys section
  3. Toggle on OpenAI API Key, then:
    • Paste your Requesty API key into the OpenAI API Key field
    • Toggle on Override OpenAI Base URL and set it to:
Cursor API Keys settings with the Requesty base URL

​
3. Add models

In the Models section, click + Add model and enter a Requesty model ID from the Model Library, for example:
  • anthropic/claude-sonnet-4-5
  • openai/gpt-5.2
  • google/gemini-2.5-pro

​
4. Select a model

Open the model picker in the chat or agent panel and select one of the models you added. Your requests now route through Requesty, and every interaction shows up in your Analytics dashboard.

​
Why use Requesty with Cursor?

​
Access to 300+ models

Cursor’s built-in BYOK only supports a handful of providers. With Requesty, you get access to 300+ models across dozens of providers, all through the single OpenAI provider override.

​
Provider failover

If one provider is unavailable or rate-limited, Requesty automatically routes to another, keeping your coding sessions uninterrupted. See Fallback Policies for details.

​
Organizational controls

For teams, Requesty provides centralized budget management. Set spending limits, manage approved models, and monitor usage across developers from the Requesty platform.

​
Usage visibility

Track which models your team uses, monitor costs in real time, and understand usage patterns from a single dashboard, regardless of the underlying provider.

​
Limitations

  • Tab completions are not affected by BYOK settings; they always use Cursor’s built-in models.
  • Auto mode may not be routed through your API key. Check Cursor’s docs for current behavior.

​
Troubleshooting

  • “Invalid API key”: Make sure you’re using your Requesty API key (starts with rqsty-sk-...), not an OpenAI key.
  • Model not found: Ensure the model ID exactly matches the format in the Model Library, for example anthropic/claude-sonnet-4-5.
  • Base URL: The override URL must be https://router.requesty.ai/v1. Make sure the /v1 suffix is included.

​
Resources

Last modified on July 20, 2026