Connect Cursor to Scenepond
Configure a custom base URL and model for supported Cursor chat features.
Official integration documentation- API base URL
https://scenepond-api-production.up.railway.app/v1- API protocol
- OpenAI Chat Completions
- Model ID
YOUR_MODEL_ID· Use the exact catalog ID
Cursor can use a custom OpenAI-compatible endpoint for supported chat features. Add a Scenepond model manually, then select it in Chat.
This guide assumes the client is installed and can start locally. You also need a Scenepond account, an enabled chat model, an API key with access, and sufficient balance for your first request.
Client installation and first launch ↗Set up with your coding agent
Copy this setup brief to the coding agent you already use. It contains the endpoint and instructions, without your API key. You can also follow the manual steps below.
Help me connect Cursor to Scenepond using its custom provider. Scenepond guide: https://open.scenepond.ai/en/integrations/cursor Official integration documentation: https://cursor.com/help/models-and-usage/api-keys API base URL: https://scenepond-api-production.up.railway.app/v1 Model ID: YOUR_MODEL_ID API protocol: OpenAI Chat Completions Inspect the installed client version and existing configuration first. Preserve other providers, agents, channels, and settings. Replace YOUR_MODEL_ID only with an enabled Scenepond model permitted by my API key. Verify tool support and actual context limits; do not invent capabilities. I will set the raw key in SCENEPOND_API_KEY or the client’s secure credential field. Do not ask me to paste it into this conversation, print it, commit it, or embed it in browser code. Follow the Scenepond guide for this client’s provider syntax and secret handling. Use the /v1 base URL and chat completions protocol with Scenepond credentials, rather than upstream provider credentials. Validate configuration locally first. Ask before making a paid API request. If a model or credential is missing, explain what I need to configure. Do not retry requests automatically. Report the changed settings, how to start a fresh session, and what has and has not been verified.
1. Prepare your model and API key
Copy an enabled model ID from the catalog and create a Scenepond API key with access to it. Agent tasks need a model with verified tool-calling support; check context limits and supported protocols before choosing.
Replace YOUR_MODEL_ID with the exact configured ID. These instructions configure a chat endpoint; they do not enable image or video generation tools. Model access and successful calls depend on backend configuration and account balance.
2. Configure the custom provider
Open Cursor Settings → Models → API Keys. Set OpenAI API Key to your raw Scenepond key, save it, and enable it. Enable Override OpenAI Base URL and enter the /v1 address below.
- OpenAI API Key
- Your Scenepond API key, without the Bearer prefix
- Override OpenAI Base URL
https://scenepond-api-production.up.railway.app/v1- Add Custom Model
YOUR_MODEL_ID
Search for the exact Scenepond model ID and choose Add Custom Model, then enable it. Cursor does not discover the gateway catalog through Refresh Model List. Use the base URL without /chat/completions or an OpenRouter-specific /cursor suffix.
Cursor custom keys do not replace its Tab autocomplete models. The OpenAI override can affect other model selections; disable the OpenAI key when returning to Cursor-hosted models that conflict with it. Requests and credentials pass through Cursor services, so this is not a local-only credential flow.
Cursor documents standard chat support for OpenAI keys. Verify reasoning, vision, and tool compatibility separately with your chosen model; this guide does not establish support for every Cursor feature.
3. Choose the model in Chat
Start a new Chat and select the exact custom model you added. Send the short test below before using an Agent workflow that reads files, changes code, or runs commands.
Official custom gateway setup ↗4. Confirm the response and usage
Confirm that the client has selected your Scenepond provider and exact model ID. Send this short message in a new session; the request uses your account balance.
Reply READY without using tools.Check that a text reply arrives, then open Scenepond usage records and match the model and request time. Review the actual settled charge. A text reply verifies basic chat access; test tools and reasoning separately only when the model supports them.
Common setup issues
- Missing key or rejected credentials
- Check that the running client can read the raw key and that the Scenepond key is enabled. Keep the secret out of diagnostic output.
- Model unavailable
- Check the exact catalog ID, key permissions, and balance. For OpenClaw, the model reference also needs the scenepond/ prefix.
- Custom model missing or built-in chat fails
- Add and enable the exact custom model manually, then select it in Chat. Check whether the OpenAI base URL override is affecting another model; disable its key when returning to a conflicting Cursor-hosted model.
- Chat works, tools fail
- Check the selected model’s tool support and the client’s tool settings. Successful text chat does not establish support for every agent capability.