Connect OpenClaw to Scenepond
Connect your personal assistant to an enabled model through a custom provider.
Official integration documentation- API base URL
https://scenepond-api-production.up.railway.app/v1- API protocol
- OpenAI Chat Completions
- Model ID
deepseek-flash· Use the exact catalog ID
OpenClaw is a personal assistant you run on your devices. Its Gateway connects the assistant to your selected Scenepond model.
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 OpenClaw to Scenepond using its custom provider. Scenepond guide: https://open.scenepond.ai/en/integrations/openclaw?model=deepseek-flash Official integration documentation: https://docs.openclaw.ai/concepts/model-providers/custom-providers API base URL: https://scenepond-api-production.up.railway.app/v1 Model ID: deepseek-flash API protocol: OpenAI Chat Completions Inspect the installed client version and existing configuration first. Preserve other providers, agents, channels, and settings. Confirm that my API key permits the selected model. 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.
Use deepseek-flash from the catalog and confirm that your API key has access. These instructions configure a chat endpoint; image and video tools require their own setup.
2. Configure the custom provider
Merge these fields into ~/.openclaw/openclaw.json, or your configured OpenClaw config file. Preserve other providers, agents, channels, and secrets settings.
1{
2 "models": {
3 "mode": "merge",
4 "providers": {
5 "scenepond": {
6 "baseUrl": "https://scenepond-api-production.up.railway.app/v1",
7 "api": "openai-completions",
8 "auth": "api-key",
9 "authHeader": true,
10 "apiKey": {
11 "source": "env",
12 "provider": "default",
13 "id": "SCENEPOND_API_KEY"
14 },
15 "models": [
16 {
17 "id": "deepseek-flash",
18 "name": "deepseek-flash"
19 }
20 ]
21 }
22 }
23 },
24 "agents": {
25 "defaults": {
26 "model": {
27 "primary": "scenepond/deepseek-flash"
28 }
29 }
30 }
31}Make SCENEPOND_API_KEY available to the OpenClaw process or ~/.openclaw/.env. The SecretRef reads the raw key from that variable; do not put the secret into the copied JSON. If your environment reader restricts variables, allow SCENEPOND_API_KEY in its configuration.
SCENEPOND_API_KEY=YOUR_SCENEPOND_API_KEYChoose openai-completions for the chat completions endpoint. The model reference is scenepond/deepseek-flash. Keep the scenepond/ prefix when the model ID contains a slash. Add verified context and output limits before relying on client defaults.
3. Select the model and start a session
1openclaw config validate
2openclaw models list --provider scenepond
3openclaw models set 'scenepond/deepseek-flash'OpenClaw TUI needs a running Gateway. Start openclaw gateway in one terminal, then run openclaw tui in another. If you already use a managed Gateway service, apply the environment through its normal restart process instead.
openclaw gatewayopenclaw tuiRun these commands where OpenClaw can read the configured environment. Replace the model ID, then start a small conversation and check the response and Scenepond usage records before enabling a longer agent workflow.
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.
- TUI cannot connect
- Check that the OpenClaw Gateway is running and can read SCENEPOND_API_KEY. Apply environment changes through the managed service’s normal restart process.
- 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.