Token costs slowing you down?
Get more out of OpenCode.
You have more work for OpenCode than you want to pay for in tokens. Standard Compute makes your compute go further, so you can tackle more tasks and take another iteration in the projects you already work on.
From $19/month · Smart routing · Automatic provider selection
Open the provider picker
Start OpenCode in your project. Type:
/connectSearch for Standard Compute.
Paste your API key
Copy your key from the Standard Compute dashboard and paste it into OpenCode.
Open my setup guide →Your real key stays in your local client.
Choose the model
Type:
/modelsSelect Standard Compute. Try a small task, then check your dashboard usage.
Native model listing checked with OpenCode 1.18.18. Full model ID: standardcompute/standardcompute. If the provider is missing, update OpenCode or use the custom setup below.
Using a different coding agent?
Compare agent costs and billing options →Need a custom provider? Build an OpenCode config
Choose your OpenCode version, API base URL and model. Copy or download the settings file for any compatible Chat Completions provider. The generator works without an account.
Check your version with opencode --version. V1 and V2 use different configuration fields.
Enter the variable name only. Set its value locally before starting OpenCode. This tool does not need your API key.
{
"$schema": "https://opencode.ai/config.json",
"model": "standardcompute/standardcompute",
"provider": {
"standardcompute": {
"npm": "@openrouter/ai-sdk-provider",
"name": "standardcompute",
"options": {
"baseURL": "https://api.stdcmpt.com/v1",
"apiKey": "{env:STANDARDCOMPUTE_API_KEY}"
},
"models": {
"standardcompute": {
"name": "standardcompute",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
}
}
}
}
}
}
Generated in your browser. No signup required.
Use your generated configuration
- Set the API key environment variable locally using your shell or secret manager. Start OpenCode from the environment that contains it.
- Merge the generated fields into your project's
opencode.json, or your global~/.config/opencode/opencode.json. Keep existing provider, permission and other settings. - Restart OpenCode and select the provider/model in
/models. Run a small task to check authentication, tool calls and streaming before a large job.
This generator prepares configuration; it does not connect to your provider or validate model access. Use the provider's exact model ID and base URL. Responses-only or Anthropic Messages endpoints need a different adapter.
For a custom model, check its context limit, image support and other capabilities in the provider's documentation before larger tasks. The minimal export does not supply those model-specific settings. V1's public schema may flag a custom default model that is absent from its built-in catalog.
Why are there two formats?
V1 uses provider, npm and options. V2 uses providers, package and settings. Choose the format for your installed version. The V2 example follows the V2 documentation; the shared public JSON schema currently describes V1, so the V2 download omits that schema reference.
Configuration references checked October 14, 2026, against OpenCode 1.19 and 2.0.29. V1 providers · V1 environment variables · V2 providers · V2 configuration.
Compare what a completed task actually costs
Try the same task and repository revision with each setup. Record retries, token categories, elapsed time and whether the result passed your acceptance check. Keep subscription fees separate from token-price estimates.
Your next feature needs compute. Make it go further.
Get more room for implementation, testing and iteration from your AI spend. Standard Compute makes that possible by comparing provider prices automatically and routing work across efficient and frontier models. Plans start at $19/month with $20 in monthly compute; larger plans provide more capacity.