Connect OpenCode to Scenepond
Connect your terminal coding agent through an OpenAI-compatible 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
OpenCode runs coding tasks in your terminal. This guide uses the 1.x custom-provider format; version 2 uses different configuration fields.
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 OpenCode to Scenepond using its custom provider. Scenepond guide: https://open.scenepond.ai/en/integrations/opencode?model=deepseek-flash Official integration documentation: https://opencode.ai/docs/providers/#custom-provider 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 this configuration into ~/.config/opencode/opencode.json, or opencode.json in your project. Preserve existing providers and settings. Check opencode --version before using this 1.x example.
1{
2 "$schema": "https://opencode.ai/config.json",
3 "model": "scenepond/deepseek-flash",
4 "provider": {
5 "scenepond": {
6 "npm": "@ai-sdk/openai-compatible",
7 "name": "Scenepond",
8 "options": {
9 "baseURL": "https://scenepond-api-production.up.railway.app/v1",
10 "apiKey": "{env:SCENEPOND_API_KEY}"
11 },
12 "models": {
13 "deepseek-flash": {
14 "name": "deepseek-flash"
15 }
16 }
17 }
18 }
19}Set the raw key in SCENEPOND_API_KEY in the environment that starts OpenCode. The {env:SCENEPOND_API_KEY} reference reads it without embedding a secret in the JSON file.
export SCENEPOND_API_KEY="YOUR_SCENEPOND_API_KEY"Before running an OpenCode agent, obtain the model’s verified context and output limits and set its limit.context and limit.output fields. The minimal configuration omits unknown values; if the operator has not supplied them, pause and request them. Client defaults do not establish model capacity.
3. Check configuration and select the model
opencode --version\nopencode models scenepondThe list should include scenepond/deepseek-flash. This checks local model registration, without verifying the key or remote access. Keep the scenepond/ prefix even if the actual model ID contains a slash.
After confirming the model limits, start opencode and use /models to select the configured Scenepond model. A new message makes an API request and may incur a charge.
OpenCode 2 migration reference ↗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.
- Provider not listed or limits unknown
- Check the installed major version, config location, provider.scenepond fields, and scenepond/ model reference. Obtain verified context/output limits before starting agent tasks; listing a model does not prove API access.
- 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.