Does Kimi Code CLI work with Standard Compute?

Yes. Kimi Code CLI supports a custom OpenAI-compatible base URL, so it works with Standard Compute. Set the base URL to https://api.stdcmpt.com/v1, paste your API key, and set the model to "standardcompute".

What base URL do I use for Kimi Code CLI?

Use https://api.stdcmpt.com/v1 as the OpenAI-compatible base URL in Kimi Code CLI, with your Standard Compute API key and the model "standardcompute".

Do I need to change my code or model names?

No code changes. The model "standardcompute" routes each request to a frontier or an efficient model, so you don't pick or update model names; an exact model ID from the Models page pins one model instead.

← All integrations

OpenAI-compatible · Custom base URL · Terminal coding agent

Use Standard Compute with Kimi Code CLI

Moonshot AI's terminal coding agent (the kimi command), which replaced the archived Python Kimi CLI and connects to any OpenAI Chat Completions provider. Paste three settings into Kimi Code: the base URL, your Standard Compute API key and the model.

In Kimi Code, type = "openai" speaks the OpenAI Chat Completions protocol. Credentials come only from api_key or the variable named in api_key_env; Kimi Code does not fall back to other shell variables.

Connect Kimi Code

Eligible new accounts can try $0.25 of compute, with no card. See trial terms →

Your connection settings

Copy these values, then put them where Kimi Code expects them (steps below).

Base URL

https://api.stdcmpt.com/v1

API Key

Your Standard Compute key

Model

standardcompute

Where to set them in Kimi Code

Open ~/.kimi-code/config.toml (create it if it doesn't exist).
Add [providers.standardcompute] with type = "openai", base_url = "https://api.stdcmpt.com/v1" and api_key_env = "STANDARDCOMPUTE_API_KEY".
Add [models.standardcompute] with provider = "standardcompute", model = "standardcompute", max_context_size = 200000 and capabilities = ["tool_use"], and set default_model = "standardcompute".
Export STANDARDCOMPUTE_API_KEY and run kimi. Use -m with a model alias to switch models for a session.

Kimi Code docs ↗

What changes in Kimi Code

Billing: Kimi Code requests draw on one monthly compute budget, with plans from $19 a month. There is no per-token bill. When the budget is used, requests stop until renewal or an upgrade, unless you turn on pay as you go.
Models: The model standardcompute picks a frontier or an efficient model for each request. An exact model ID from the Models page pins one model instead.
Good to know: Kimi Code matches thinking, vision and tool use by model name, so declare capabilities on gateway model IDs it may not recognise. To pin Kimi K3, add a second model alias with model = "moonshotai/kimi-k3" and capabilities such as tool_use, thinking and image_in. Logging in with a Kimi membership is the separate native route.