When to Use
Dify is a platform for building apps and orchestrating workflows and agents. Once you integrate Tokener CA into Dify, you can use platform models in chat apps, Workflows, Agents, and knowledge base pipelines.
If your Dify environment can access the plugin marketplace, install the Tokener CA plugin and use it directly; if you can't install plugins, integrate manually as an OpenAI-compatible provider instead.
Option 1: Install the Tokener CA Plugin (Recommended)
The Tokener CA plugin is already available in the Dify Marketplace:
The Tokener CA plugin integrates into Dify as a model provider. After installing it, you can directly select a preset Tokener CA chat model and continue to use Dify's streaming output, tool calling, and Workflow / Agent orchestration capabilities.
Install the Plugin
- Open your Dify workspace.
- Go to
PluginsorMarketplaceand search forSkypool; you can also open the marketplace link above directly. - Click
Installand choose the workspace to install to. - After installation, find
Skypoolon Dify's model provider or plugin configuration page.
Configure Credentials
| Setting | How to Fill It In |
|---|---|
| Consumer API Key | Enter your Tokener CA Consumer API Key, for example stc-... |
| Endpoint URL | Usually keep the plugin default; if you need to enter it manually, use https://a.skypool.xyz/v1 |
| Model | Prefer a built-in Tokener CA chat model from the plugin |
Only change the Endpoint URL to the corresponding Tokener CA-compatible address if you're using a private deployment or test environment. Do not enter the full /chat/completions path.
Use It in a Dify App
- Create or open a Chat App, Workflow, or Agent.
- In the model picker, select a model under the
Skypoolprovider. - After saving the app configuration, send a simple message to verify the model responds normally.
For your first test, we recommend creating the simplest possible Chat App and sending:
In one sentence, confirm that this app has been successfully integrated via the Tokener CA plugin.Option 2: Manual Integration as an OpenAI-Compatible Provider
This path is for cases where you can't install the plugin for now, need to configure it manually on Dify's model provider page, or need compatibility with older versions of Dify.
We recommend configuring Tokener CA as an OpenAI-compatible provider in Dify:
| Setting | Value |
|---|---|
| Provider | OpenAI, or OpenAI-API-compatible if your version shows it |
| API Key | Consumer API Key, for example stc-... |
| Base URL | https://a.skypool.xyz/v1 |
| Model | Platform model name, for example gemma4:26b |
Add the Model Provider in Dify
Open your Dify workspace and configure it as follows:
- Open
Settings. - Go to
Model Providers. - Select
OpenAI, orOpenAI-API-compatibleif your version offers it. - Add a new set of credentials.
- Enter your Consumer API Key for the API Key.
- Enter
https://a.skypool.xyz/v1for Custom Base URL or API Base. - Save and test the connection.
Dify validates the credentials when you save. If validation fails, first run the curl at the end of this article with the same key and model to confirm that the platform-side call already works.
Add or Select a Model
If the Tokener CA model ID isn't in Dify's model list, you'll need to add a custom model manually.
Suggested fields:
| Field | Value |
|---|---|
| Model Type | LLM or Chat Model |
| Model Name / Model ID | gemma4:26b |
| Completion Type | Chat |
| Context Size | Fill in per the model page; if unsure, start with 32768 or 128000 |
| Max Tokens | Start with 4096 or 8192 |
After adding it, select the model in your app's model picker.
Use It in an App
Create or open a Dify App and select the Tokener CA model you just integrated in the model configuration. We recommend testing with the simplest Chat App first:
In one sentence, confirm that this app has been integrated with Tokener CA.Once the test passes, use it in Workflows, Agents, tool calling, or knowledge base Q&A.
Verify the API
If Dify configuration fails, first verify the same key and model from a terminal:
curl -X POST "https://a.skypool.xyz/v1/chat/completions" \ -H "Authorization: Bearer <consumer_api_key>" \ -H "Content-Type: application/json" \ --data-raw '{ "model": "gemma4:26b", "messages": [ { "role": "user", "content": "Return a short message confirming the integration works." } ], "max_tokens": 64, "stream": false }'Troubleshooting Checklist
| Symptom | How to Fix |
|---|---|
| Saving credentials fails | Check the API Key, balance, and Base URL |
| Model not in the list | Use the custom model feature to add the platform model ID manually |
404 | Base URL should be https://a.skypool.xyz/v1, not the full chat endpoint |
| Workflow run fails | Verify with a plain Chat App first, then check the node's model configuration |
| Knowledge base embedding fails | A chat model can't be used directly as an embedding model; confirm whether an embedding model is available |