Which API should you use with Factory Droid?

To run Factory Droid on one monthly model bill, add Standard Compute to customModels in ~/.factory/settings.json with provider generic-chat-completion-api and baseUrl https://api.stdcmpt.com/v1, from $19 a month with a $20 compute budget. Factory's own plans run $20, $100 and $200 a month with Factory-hosted models. The catch: Factory says bring-your-own-key use is free only up to an allowance on its Individual plans and is then charged according to your plan, and it does not publish the allowance size.

Guide updated 2026-10-14. Check each provider's current terms below.
Light or occasional use
If Droid's usage fits inside Factory Pro's included usage, the $20 plan is the simplest bill. Check Factory's usage page after a busy week before adding a second provider.
One fixed monthly bill
For long Droid sessions on Claude or GPT, a Standard Compute custom model keeps the model bill at the plan price, and requests stop at the monthly compute budget instead of billing overage. Watch Factory's own BYOK allowance as well, since that is billed separately by Factory.

API and subscription options for Droid

OptionPriceWhat you get
Factory plans$20 / $100 / $200 per moPro, Plus (about 5x Pro's usage) and Max (about 10x) include Factory-hosted model usage. Bring-your-own-key use is free up to an allowance on all Individual plans, then charged according to the plan; Factory does not publish the allowance size. Source: factory.com
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
Anthropic APIPay-as-you-goDirect API access for supported Claude models. Token use, model choice, service limits and spending controls determine the cost and available throughput. Source: claude.com

Prices and allowances can change. Factory's plan prices and BYOK allowance terms were read from factory.com/pricing, and the customModels fields from Factory's BYOK docs, on October 14, 2026. Factory pricing · Factory: bring your own key. Spot an error? Tell us.

Add Standard Compute to Droid's custom models

~/.factory/settings.json
{
  "customModels": [
    {
      "model": "standardcompute",
      "displayName": "Standard Compute",
      "baseUrl": "https://api.stdcmpt.com/v1",
      "apiKey": "${STANDARDCOMPUTE_API_KEY}",
      "provider": "generic-chat-completion-api",
      "maxOutputTokens": 16384
    }
  ]
}

Export STANDARDCOMPUTE_API_KEY, start droid, run /model and pick it under Custom models. Add one entry per pinned model, for example anthropic/claude-sonnet-5.5.

Droid questions

Which provider value do I use in Droid's customModels for an OpenAI-compatible endpoint?
generic-chat-completion-api, for the Chat Completions API. Factory's docs say to use it unless you are calling OpenAI's or Anthropic's official API. The value openai switches Droid to the OpenAI Responses API, and anthropic to the Messages API. Standard Compute serves Chat Completions and Responses at https://api.stdcmpt.com/v1, so either of the first two works; generic-chat-completion-api is the safe default.
Do I still pay Factory if I bring my own key to Droid?
Possibly. Factory's pricing FAQ says all Individual plans include an allowance of free BYOK usage, after which BYOK usage is charged according to your plan, and the allowance size is not published. Your model provider bills its part separately: on Standard Compute that is the plan price, with new requests stopping at the monthly compute budget.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Droid 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 keyDroid 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 →