Using Downsizing with TypingMind

Prerequisites

A TypingMind account (cloud app at typingmind.com, or self-hosted "TypingMind Custom") and a Downsizing account that can make requests (pay-per-use or a connected subscription both work). Grab your Router ID and API key by running ds link typingmind in a terminal, or from the Inference API page.

TypingMind runs in your browser (or its own app storage) — there's no local config file on your machine for ds to write to. Instead, the ds CLI prints the exact values you paste into TypingMind's Add Custom Model form, and TypingMind stores the connection itself.

1. Get your setup values

Run the following to print the values you'll paste into TypingMind:

ds link typingmind

This prints an Endpoint URL, a Model ID, a Context Length, and an Authorizationheader value — everything TypingMind's Custom Model form asks for. Safe to run more than once; it doesn't write any files.

2. Add a Custom Model in TypingMind

1. Open TypingMind and click the gear icon → Settings → Models → Add Custom Model.
2. Set Name to something recognizable, e.g. Downsizing.
3. Set Endpoint to your Downsizing OpenAI-compatible Chat Completions route:

http://localhost:3001/YOUR_ROUTER_ID/openai/v1/chat/completions

Replace YOUR_ROUTER_ID with the Router ID printed by ds link typingmind(or from the dashboard). TypingMind's Custom Model client always sends OpenAI Chat Completions–shaped requests to this endpoint, so use the /openai/v1/chat/completionsroute rather than the Anthropic Messages route — that's a requirement of TypingMind's client, not a Downsizing limitation.

4. Set Model ID to the model you want to route through Downsizing, e.g. claude-opus-4-8, and Context Length to 200000 (adjust for whichever model you pick).
5. Under Custom Headers, add a row with your Downsizing API key:

Authorization: Bearer dws_your_api_key_here

Replace dws_your_api_key_here with your real Downsizing API key (starts with dws_). Click Test, then Add Model.

Verify

Start a new chat in TypingMind, pick the Downsizing custom model you just added from the model picker, and send a test message. If you get a response, the connection is wired up correctly. Then check your savings dashboard to see the request appear in your usage metrics.

Removing the connection

Running ds unlink typingmindupdates Downsizing's own record of linked tools, but since TypingMind stores the Custom Model in its own account storage, you'll also want to open TypingMind → Settings → Models and delete the Downsizing custom model there.