Which API should you use with ZCode?

For Z.ai's ZCode with more than GLM models, the best API is a cost-optimized custom provider: in Settings → Model Providers → Add Provider, set the OpenAI endpoint to https://api.stdcmpt.com/v1, add your key and the model standardcompute, and Standard Compute's 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. ZCode's native route is a Z.ai account with a free daily trial quota and the GLM Coding Plan (Lite, Pro and Max, with 5-hour and weekly credit limits). ZCode is free and open source (Apache 2.0).

Light or occasional use

If GLM models handle your tasks, the GLM Coding Plan's Lite tier is the simplest bill, and new Z.ai users get a free daily trial quota inside ZCode to test first.

Daily use, cost-optimized

When you want Claude, GPT, DeepSeek or Kimi in ZCode next to GLM, 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: requests stop with HTTP 402 when the compute budget is used, with nothing billed on top.

API and subscription options for ZCode

Prices and allowances can change. ZCode's provider fields, config file and thinking-effort behavior come from ZCode's configuration docs, and GLM Coding Plan limits from Z.ai's docs, read on October 15, 2026. ZCode: model configuration · GLM Coding Plan · ZCode repo. Spot an error? Tell us.

Add Standard Compute as a ZCode custom provider

Name             Standard Compute
OpenAI endpoint  https://api.stdcmpt.com/v1
API key          sc_live_…            (your Standard Compute key)
Add Model        standardcompute      (or anthropic/claude-sonnet-5.5)
Enable           on

Save, then pick the model in ZCode's model selector. ZCode stores the provider in ~/.zcode/v2/config.json.

ZCode questions

Can I add custom request parameters such as reasoning_effort to a ZCode custom provider?

Not yet. In ~/.zcode/v2/config.json a provider's options only recognize connection settings: apiKey, baseURL, apiKeyRequired and headers; other keys added by hand are not applied. ZCode sets thinking effort itself for models it knows (on OpenAI-compatible endpoints through reasoning_effort); other custom models get a simple on/off toggle or no levels.

Can I change the context window of a custom model in ZCode?

Yes. Open the model under Settings → Model Providers and expand Advanced: custom-provider models are editable and the value applies to new sessions. Built-in Coding Plan models are different: their context window comes from the server, so local edits are restored on the next sync.