Which API should you use with goose?

For daily goose sessions on one monthly price, the best API is a flat-rate OpenAI-compatible provider such as Standard Compute, added as a goose custom provider at https://api.stdcmpt.com/v1, from $19 a month with a $20 compute budget. goose's onboarding recommends Agent Router by Tetrate, which starts you on $10 of free credits and then bills per token, and OpenRouter is pay-per-use too. A local model through Ollama costs nothing per token if your hardware can run it. goose itself is free, so the provider is the whole bill.

Guide updated 2026-10-14. Check each provider's current terms below.
Light or occasional use
For a few sessions a week, Tetrate's free credits and then a pay-per-token router will likely cost the least. If you have a capable GPU, try a local model on a real task before paying for anything.
One fixed monthly bill
Once goose runs long recipes or extension-heavy sessions every day, a Standard Compute key keeps the bill at the plan price. Requests stop with HTTP 402 when the monthly compute budget is used; running requests finish and nothing is billed on top.

API and subscription options for goose

OptionPriceWhat you get
Agent Router by Tetrate$10 free credits, then per tokenThe route goose's onboarding recommends. You get $10 in free credits the first time you authenticate with Tetrate through goose; after that, usage is billed per token at the router's rates. Source: goose-docs.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
Local model (Ollama / vLLM)Hardware + electricityNo hosted per-token bill, but hardware, context capacity, throughput and maintenance still limit what you can run. Test task quality on your own hardware. Source: docs.ollama.com

Prices and allowances can change. goose's custom provider format, key storage and the Tetrate credit offer come from goose's provider and config-file docs, read on October 14, 2026. goose: providers · goose: config files. Spot an error? Tell us.

Add Standard Compute as a goose custom provider

~/.config/goose/custom_providers/standardcompute.json
{
  "name": "standardcompute",
  "engine": "openai",
  "display_name": "Standard Compute",
  "api_key_env": "STANDARDCOMPUTE_API_KEY",
  "base_url": "https://api.stdcmpt.com/v1",
  "models": [
    { "name": "standardcompute", "context_limit": 200000 },
    { "name": "anthropic/claude-sonnet-5.5", "context_limit": 200000 }
  ],
  "supports_streaming": true
}

Then export STANDARDCOMPUTE_API_KEY with your key and start goose with GOOSE_PROVIDER=standardcompute GOOSE_MODEL=standardcompute. goose configure → Custom Providers → Add A Custom Provider → OpenAI Compatible writes the same file for you.

goose questions

Why does goose say "No api key passed in" with my custom OpenAI-compatible provider?
Because goose does not read provider keys from config.yaml: a key written there is ignored. goose reads a custom provider's key from the system keychain, or from the environment variable named in the provider file's api_key_env. When you add the provider with goose configure, goose names it custom_<name> and the variable CUSTOM_<NAME>_API_KEY, so a provider called standardcompute becomes custom_standardcompute with CUSTOM_STANDARDCOMPUTE_API_KEY. Export that variable, or re-enter the key in goose configure, and the 401 goes away.
Is goose free to use?
Yes. goose is free and open source (Apache 2.0), and its docs note that not every provider has a free tier, so the model is what you pay for. On Standard Compute that is one plan price from $19 a month with a $20 compute budget; at the budget, new requests get HTTP 402 instead of an overage bill.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed goose 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 keygoose 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 →