Which API should you use with Command Code?

For Command Code with your own key, the best API for mixed daily work is a cost-optimized BYOK provider: add Standard Compute in /connect or ~/.commandcode/providers.json with baseURL https://api.stdcmpt.com/v1 and the model standardcompute, and its router sends each step to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), on a plan from $19 a month with a $20 compute budget. Command Code's own plans ($1 to $200 a month) include credits with 5-hour and weekly limits, and its Provider plan ($15 a month with $15 of usage included) bills the model you pick at list rates with no markup. BYOK requests go straight from your machine to the provider.

Guide updated 2026-10-15. Check each provider's current terms below.
Get your API key$0.25 trial for eligible new accounts, no card. Plans from $19/mo.
Light or occasional use
If one model you already know covers your work, Command Code's Provider plan bills it at the model's own rates with no markup, which is hard to beat on price for that model. For a few sessions a week, the $1 Go plan's $10 of credits may be enough.
Daily use, cost-optimized
When cmd runs long sessions every day and you would rather not pick the model for each step, a Standard Compute provider sends each step to the cheapest model that can do it, and for every model we vet providers for price, uptime and speed, with automatic fallback. Opt-in Europe or US Compliance rules apply per key, team or company, and we don't train on your prompts or store them. The bill stays at the monthly plan price instead of pay-as-you-go top-ups: requests stop with HTTP 402 when the compute budget is used, with nothing billed on top.

API and subscription options for Command Code

OptionPriceWhat you get
Command Code plans$1 / $10 / $20 / $100 / $200 per moGo, GOAT, Pro and Max subscriptions (plus a processing fee) include monthly credits, for example $10 on Go, $80 on Pro and $300 on Max 20×, spent on Command Code's catalog models with per-model allowances and 5-hour and weekly limits. Source: commandcode.ai
Command Code Provider plan$15/mo, then pay as you goCommand Code's API plan: $15 a month plus a processing fee, with $15 of usage included, then requests bill at the underlying model's rates with no markup. Top-ups roll over. You pick the model; nothing routes for cost. Source: commandcode.ai
Standard Compute (us)From $19/moSmart routing sends each request to the cheapest model that can do it, or pin any model by its exact ID. Standard Compute starts at $19/month with a $20 monthly compute budget. Requests stop when that budget is exhausted until renewal or a plan change; there are no automatic overage charges. Requests are not slowed as the budget is used. It is a fixed bill with a finite allowance.
OpenRouterPay-as-you-goChoose models and providers through one API. Usage-based pricing can suit light or bursty work; estimate long agent sessions and review current fees and limits. Source: openrouter.ai

Prices and allowances can change. Command Code's BYOK schema, key storage and local-only mode come from its BYOK docs; plan prices and the Provider plan terms from its pricing page and Provider API docs, all read on October 15, 2026. Command Code: BYOK providers · Command Code: Provider API · Command Code pricing. Spot an error? Tell us.

Add Standard Compute as a Command Code BYOK provider

~/.commandcode/providers.json
{
  "provider": {
    "standardcompute": {
      "name": "Standard Compute",
      "baseURL": "https://api.stdcmpt.com/v1",
      "apiKey": "$STANDARDCOMPUTE_API_KEY",
      "models": {
        "standardcompute": { "name": "Standard Compute (routed)", "contextWindow": 200000 },
        "anthropic/claude-sonnet-5.5": {},
        "deepseek/deepseek-v4-pro": {}
      }
    }
  }
}

Export STANDARDCOMPUTE_API_KEY, reopen /model and pick standardcompute/standardcompute. Or run /connect → (BYOK) Add your own provider, name it standardcompute, keep the OpenAI-compatible wire, paste https://api.stdcmpt.com/v1 and your key: cmd stores the key in ~/.commandcode/auth.json and imports the model list from the endpoint.

Command Code questions

Do Command Code BYOK requests go through Command Code's servers?
No. Command Code's docs say BYOK requests go straight from your machine to the provider's endpoint with your key, and keys never leave the machine. The only thing sent to Command Code is a trimmed telemetry span (model id, provider id, usage, latency, finish reason); DO_NOT_TRACK=1 or cmd --local-only turns that off too.
Why does Command Code ignore the API key I wrote into providers.json?
providers.json only takes a reference to a key: "$STANDARDCOMPUTE_API_KEY", "{env:STANDARDCOMPUTE_API_KEY}" or "!command". A raw secret pasted into the file is refused with a warning and the key is ignored. Export the variable, or paste the key in /connect, which stores it in ~/.commandcode/auth.json; a stored key wins over the file's reference.
Is Command Code's Provider plan cheaper than a fixed plan?
For one model you have already chosen, often yes: it bills that model at its underlying rates with no markup, after $15 a month that includes $15 of usage. The difference is who picks the model and how the bill behaves. Standard Compute's router picks the cheapest model that can do each step and the price stays at the plan (from $19 a month with a $20 compute budget), with HTTP 402 at the budget; the Provider plan grows with your usage through top-ups.
Do sub-agents and compaction in Command Code use my BYOK model?
Yes. While a BYOK model is active, compaction, summarization, sub-agents and title generation all default to the session model, so nothing silently falls back to Command Code's models or bills your Command Code plan mid-session.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Command Code version.
  2. Run a small task on a clean branch and review the result, elapsed time and compute used.
  3. Estimate your actual monthly workload before selecting a larger allowance.
Get your API keyCommand Code setup guide →Compare compute budgets →

Record your own results with the workload CSV and report template. These are blank templates, not published benchmark results.

Disclosure: this guide is maintained by Standard Compute, one of the options above. Choose based on task quality, supported features and total cost for your workload. Light usage may cost less on a usage-based API; sustained workloads need enough allowance on any subscription.

All flat-rate plans compared →The cheapest-tokens math →Plan compute for your team →