New model MiMo-V2.6 Flash is launching 
Inferway
Back to client guides
Client guides

Qoder

Why Qoder is not verified against Inferway yet, and what its custom-model options allow.

Not yet verified

Qoder IDE only offers a fixed vendor list with no custom Base URL, so it cannot connect to Inferway. The Qoder CLI accepts a custom OpenAI-compatible endpoint, but we have not verified it yet.

Use the existing API

Configuration reference for when the interface opens

Before you start

Install the named client using its official instructions. Pi here means the pi-mono coding agent; Hermes means Nous Research's Hermes Agent.

Once your Inferway account is activated, get an API key from Console → API keys. Use a dedicated key for this client and review its model access and spending limits. Both live and test prefixes use the same inference and billing path; test is an environment label, not a free or simulated inference mode.

Use an Inferway key for Inferway's endpoint. An OpenRouter key belongs to OpenRouter and cannot authenticate to this address.

Keep the key in the client's credential store or your local environment. Do not paste it into a prompt, screenshot, or committed configuration. These examples use bash/zsh on macOS or Linux.

Why this page has no configuration

Qoder IDE's custom models only offer a fixed list of vendors — there is no custom Base URL field — so it cannot point at Inferway.

The Qoder CLI does support a custom OpenAI-compatible endpoint, but we have not verified it yet, so this page publishes no recipe.

As the CLI implements it today, adding a bring-your-own-key model makes the client send the API key you entered, together with the Base URL, to Qoder's servers (/algo/api/v2/byok/config) for validation. Keep that in mind before pasting a key in.

We will update this page once this integration has been verified.