Standard Compute

Which API should you use with Zoo Code?

For Zoo Code on one monthly price, the best API is a flat-rate OpenAI-compatible provider: set API Provider to OpenAI Compatible with base URL https://api.stdcmpt.com/v1 and model standardcompute, from $19 a month with a $20 compute budget, shared across Architect, Code, Debug and your custom modes. Zoo Code is free and open source with your own keys; its paid parts are Zoo Gateway and Cloud Agent credits and a Team plan at $25 per seat a month. Zoo Code uses native tool calling only, so every model you pin must support tools.

Guide updated 2026-10-14. Check each provider's current terms below.
Light or occasional use
Run one full Architect, Code and Debug pass with an efficient model before buying anything. For a few tasks a week, a pay-as-you-go OpenRouter key will likely cost the least.
One fixed monthly bill
Standard Compute can bound the model bill across every Zoo Code mode, as long as a month of your tasks fits the budget. Modes do not get separate allowances, and requests stop at the monthly compute budget instead of billing overage.

API and subscription options for Zoo Code

OptionPriceWhat you get
Zoo Code (free) / Team$0, or $25 per seatThe extension is free and open source with your own keys; you pay only your provider. Team is $25 per seat a month (two-seat minimum) with a shared wallet; Zoo Gateway and Cloud Agents are paid in credits. Source: zoocode.dev
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. Zoo Code's prices were read from zoocode.dev/pricing, and the provider settings and tool-calling requirement from Zoo Code's docs, on October 14, 2026. Zoo Code pricing · Zoo Code: OpenAI Compatible provider · Zoo Code repo. Spot an error? Tell us.

Set up the OpenAI Compatible provider in Zoo Code

Zoo Code settings → API Provider: OpenAI Compatible
Base URL   https://api.stdcmpt.com/v1
API key    sc_live_…            (your Standard Compute key)
Model      standardcompute      (or an exact ID such as anthropic/claude-sonnet-5.5)

Zoo Code reads the model list from the provider, or you can type an ID. To give each mode its own model, save one configuration profile per model and assign profiles to modes.

Zoo Code questions

Is Zoo Code still maintained now that Roo Code has shut down?
Yes. Zoo Code continues Roo Code's codebase after the Roo team wound down Roo Code on May 15, 2026, and it ships regularly: v3.88.0 came out on October 10, 2026. It is on the VS Code Marketplace and Open VSX, keeps Roo's modes, and takes the same OpenAI Compatible provider settings, so a Roo setup moves over with the same base URL, key and model.
Why does Zoo Code reject a model that works in other tools?
Zoo Code uses native tool calling exclusively, with no XML fallback, so a model without tool calling cannot run in it. Pin a model you know handles tool calls, such as a current Claude, GPT or GLM model, and test one full task before switching your modes over.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Zoo 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 keyZoo 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 →