Does MiniMax Code work with Standard Compute?

Yes. MiniMax Code 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 MiniMax Code?

Use https://api.stdcmpt.com/v1 as the OpenAI-compatible base URL in MiniMax Code, 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 MiniMax Code

MiniMax's open-source terminal coding agent (mcode), which runs on MiniMax's own models after mcode login or on your own provider without a MiniMax account. Standard Compute is in MiniMax Code's provider picker: run /model, choose + Add 3rd-party provider… and pick Standard Compute under Known providers, then paste your key. The base URL and the router model come filled in from models.dev.

MiniMax Code builds its Known providers list from models.dev; in the China region it reads a MiniMax mirror of that catalog pinned to a release, so a new provider can show up there later. Custom provider with the same base URL always works.

Connect MiniMax 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 MiniMax 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 MiniMax Code

Run mcode, type /model and choose + Add 3rd-party provider… under Providers.
Type standard to filter, and pick Standard Compute under Known providers. The model screen shows the Base URL https://api.stdcmpt.com/v1 (Ctrl+E edits it) and the model standardcompute.
Press Tab to enter your Standard Compute API key, then press Enter on standardcompute for its details and Enter again to test, save and use it. A failed test saves nothing.
From the shell instead: export STANDARDCOMPUTE_API_KEY, then run mcode provider add --name standardcompute --base-url https://api.stdcmpt.com/v1 --api-format openai-completions --model standardcompute --api-key-env STANDARDCOMPUTE_API_KEY --use.

MiniMax Code docs ↗

What changes in MiniMax Code

Billing: MiniMax Code requests draw on one monthly compute budget, with plans from $19 a month. 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: For MiniMax models only, MiniMax's own M Plan or pay-as-you-go API costs less than any router. Standard Compute is for using Claude, GPT, GLM or Qwen from MiniMax Code on one key. Bringing your own key needs no MiniMax login.