Use Chatbox with Models Hub: API Host and Key Setup

Add an OpenAI API-compatible model provider in the Chatbox desktop client, enter your Models Hub API host and key, and call Claude, GPT and more with one key, with verification and troubleshooting.

Chatbox is a cross-platform desktop AI chat client that supports multiple model providers at once. Point one of its providers at Models Hub and every message you send in the chat window draws on your Models Hub balance. This is the simplest setup in this series, a good starting point if you're new to Models Hub.

Three things you need

A Models Hub API key, the base URL https://modelsok.com/v1, and a model name. The whole setup takes under a minute.

Prerequisites

Chatbox installed. Download the build for your OS from the official site.
A Models Hub API key from the Tokens page, in a group that can access the models you want.

Recommended models

Use case	Model	Pricing	Live status
First choice for everyday chat	`claude-sonnet-4-6`	Price	Availability and latency
Complex reasoning and long-form writing	`gpt-5.5`	Price	Availability and latency
Cheap and fast for simple Q&A	`gpt-5.4-mini`	Price	Availability and latency

Model names are authoritative on the pricing page.

Setup

Open Chatbox, go to Settings → Model Provider, and click "Add" at the bottom.
Set API Mode to "OpenAI API Compatible".
Paste your Models Hub key into API Key.
Enter the API Host:
```
https://modelsok.com/v1
```
Leave API Path empty; don't put /v1 in both fields. Chatbox appends its default path after the host automatically. Note: these field names come from Chatbox's official docs; treat your current version's actual controls as authoritative.
Enter or select one of the model names above in Model, then save.

Verify

Start a new chat and send something like "introduce yourself in one sentence". A normal reply means you're connected. Then check Usage logs in the Models Hub console; a request under that model name appears within seconds, confirming traffic went through Models Hub rather than Chatbox's own service.

Common errors

Symptom	Cause	Fix
`401` / invalid key	Incomplete key, stray whitespace, or a disabled token	Re-copy from the Tokens page
Spinner never resolves, or a connection error	Wrong API host, usually a missing `/v1` or an extra slash	Re-enter `https://modelsok.com/v1` and keep API Path empty
Model not found	Misspelled model name, or the token's group can't access it	Check the pricing page
Slow replies or a "too many requests" message	Rate limited by concurrency	Retry shortly; contact support for a higher limit if it persists
Nothing shows in usage logs	The chat isn't using the newly added provider	Check the chat's model source points at the provider you just added

FAQ

How is it billed? Per input and output token actually consumed in each chat, at the price on each model's pricing page. Usage logs itemize every request.

How is this different from the vendor's API directly? Same request format; only the API host changes. You don't need separate accounts with each vendor, and one key works across models.

How do I switch models? Use the model picker at the top or side of the chat window, or add several models under the same provider in settings and switch between them.