Use AstrBot with Models Hub: Model Provider Setup

Add an OpenAI model provider in AstrBot pointed at Models Hub, set it as the default chat model, and use it across QQ, Feishu, and more, with recommended models and error fixes.

AstrBot is an open-source, all-in-one agent chatbot platform that connects large model capabilities to mainstream messaging apps like QQ, Feishu, DingTalk, and WeCom. Its "Model Providers" support the standard OpenAI API; point a provider at Models Hub and every conversation flow configured in AstrBot draws on your Models Hub balance. This page covers only the connection step — see the official documentation for building bots.

Three things you need

A Models Hub API key, the endpoint https://modelsok.com/v1, and a model name.

Prerequisites

AstrBot deployed with admin panel access. If not deployed yet, see the official documentation. Project page: GitHub.
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, a balance of speed and quality	`claude-sonnet-4-6`	Price	Availability and latency
Complex reasoning and long context	`gpt-5.5`	Price	Availability and latency
Cheap and fast, good for high-frequency group chat	`gpt-5.4-mini`	Price	Availability and latency

Model names are authoritative on the pricing page.

Setup

Sign in to Models Hub, click "Console" at the top, then "Token Management" → "Add Token" to create a new API key. Select the appropriate permissions and click "Create".
Once created, click the copy button to copy the generated API key.
Open the AstrBot admin panel, go to "Model Providers", click "Add Model Provider", and choose OpenAI (AstrBot supports both the OpenAI Chat Completion and Responses APIs; Models Hub connects through this path).

In the dialog, fill in:

Field	What to enter
API Base URL	`https://modelsok.com/v1` (for a local Models Hub deployment, use the local address, e.g. `http://localhost:3000/v1`)
API Key	The Models Hub API key you just copied
Model name	One of the model names from the table above

Click "Save" when done.

Filling in API Base URL and API Key to finish the OpenAI provider setup

Go to "Configuration File", find the model section, change "Default Chat Model" to the provider you just created, and click "Save".

Verify

Send "hello" in the AstrBot admin panel's debug chat, or through a bound platform like QQ or Feishu. 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.

Common errors

Symptom	Cause	Fix
Connection failure when saving the provider	Wrong API Base URL, or a local deployment used a public address (or vice versa)	Use `https://modelsok.com/v1` for a third-party site; use a reachable local address for local deployments
`401` / Invalid API key	Incomplete key, or a disabled token	Re-copy from the Tokens page
Model not found in chat	Misspelled model name, or the token's group can't access it	Check the spelling on the pricing page
Slow replies or `429`	Rate limiting, usually from high concurrency	Retry later; contact support for a higher limit if this persists
Nothing shows in usage logs	"Default Chat Model" wasn't switched to the new provider	Go back to "Configuration File" and confirm the default chat model is the Models Hub provider

FAQ

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

How is this different from using OpenAI's official endpoint directly? Same request format; only the base URL changes, and one key can switch between Claude, GPT, and other models under the same provider.

How do I switch models? Edit the OpenAI provider you configured and change the model name, or add another provider and switch the default chat model on the "Configuration File" page.