{"slug": "using-modal-for-glm-flash-on-cadenya-s-agent-runtime", "title": "Using Modal for GLM Flash on Cadenya's Agent Runtime", "summary": "Cadenya published a walkthrough showing developers how to connect Zhipu's GLM 5.3 Flash open-weight model, hosted on Modal, to its agent runtime as an OpenAI-compatible AI provider. The guide covers creating a Modal endpoint, using Modal proxy tokens for authorization, adding the model with its 1 million token context window and prompt caching enabled, and wiring it into a Cadenya agent variation for tool-calling tasks. Cadenya developer Robert Ross wrote the post.", "body_md": "# Get to know Cadenya\n\nWe’re developers who love to build. We set out to create a yes-code platform that makes building agents feel like the best parts of building software.\n\n# Using GLM Flash on Cadenya\n\nWalkthrough\n\n``` bash\n$ whoami\n> Robert Ross\n```\n\nCadenya supports using any model in your agent variations, including open-weight models. The mystery of using these open-weight models has faded considerably, especially with companies such as [Modal](https://modal.com/) offering point-and-click options to deploy them.\n\nThis (short) post goes into how you can connect GLM 5.3 Flash, hosted on Modal, to Cadenya and use it for your agent.\n\n## Creating the endpoint\n\nModal has made it dead simple to create a private endpoint that follows the OpenAI API’s chat completion format. First, you’ll need to be logged in to your Modal account.\n\n1. Go to `https://modal.com/endpoints/{workspaceSlug}/main` .\n2. Click “Create Endpoint.”\n\nOnce you’re on the Create Endpoint page, you can select GLM and then the Flash version.\n\n*Note:* Really, any model will work in this tutorial, but we’re focused on GLM.\n\nSelect the GLM Flash model, give the endpoint a different name if you like (your prerogative), and click “Create Endpoint.”\n\n## Proxy tokens\n\nModal requires proxy tokens to access these endpoints. These token pairs can be found at `https://modal.com/settings/{workspaceSlug}/proxy-auth-tokens`. **Save the token pair for the next step.**\n\n## Add the AI provider to Cadenya\n\nCadenya supports adding OpenAI-compatible providers, including Modal. We can configure a new AI provider with our shiny new endpoint and proxy tokens to start using GLM in a few steps.\n\n1. Go to [https://app.cadenya.com/w/default/aiProviders](https://app.cadenya.com/w/default/aiProviders) .\n2. Click “Add AI Provider” in the top right.\n\nFill in the form with these values:\n\nSelect this option from the Provider dropdown.\n\nReplace the placeholder with your Modal shared endpoint URL. Be sure to include /v1 at the end.\n\nAdd a header named Authorization. Replace the placeholders with the proxy token pair you saved earlier.\n\nHere’s what mine looks like at this point:\n\nOnce you save it, you’ll be dropped into the AI provider’s details page.\n\n## Adding the model\n\nClick the “Add Model” button in the bottom left of the AI provider’s details page, and we’ll enter our details for GLM Flash.\n\nModal has a dedicated page for each model in its library with all the details we need to fill in this form.\n\nYou can find the [GLM 5.3 Flash details here](https://modal.com/library/zai/glm-5-3-flash), for example.\n\nThis must match exactly; otherwise, chat completions will fail.\n\n1 million tokens.\n\nTurn on `Prompt Caching` in the capabilities, too.\n\nUSD per million tokens.\n\nUSD per million tokens.\n\nSave the model, and let’s hook it up to an agent variation in Cadenya.\n\n## Wiring it up to an agent\n\nNow you’ll need to create an agent and a variation in Cadenya to use this model. If you already have both, you can skip this part.\n\nGo to the [New Agents page in Cadenya](https://app.cadenya.com/w/default/agents/create) and create a new agent.\n\n### The agent\n\nWe can create a straightforward agent called “GLM Test” in Cadenya (no structured outputs or episodic memory required).\n\nClick “Create Agent.”\n\n### The variation\n\nYou’ll be redirected to add the first variation to the newly created GLM Test agent. We can use these sample values to configure it:\n\nFind the model we added above and select it.\n\n## Watch it fly\n\nOnce you have an agent configured, we can dispatch an objective to it. Click the kebab menu in the top right, then click “Run.” Once the dialog appears, you can write a fake customer support message:\n\n```\nHello, my order has not arrived, and I need help. It's a shoe order, and I badly need my kicks for a wedding, or my family might disavow me. I can't be having that.\n```\n\n## GLM with tool calls\n\nCadenya is built for calling tools, and GLM Flash is very accurate at tool calling for how fast it is.\n\nNow, let’s add a tool set to our workspace to use the [free-faker-mcp](https://github.com/cadenya/free-faker-mcp) project. This is an MCP server hosted at `https://free.cadenya.com/faker-mcp` that provides tools you can easily try in your agents.\n\n### Adding the tool set\n\nVisit the [Create Tool Set](https://app.cadenya.com/w/workspace_01M272W32Y1WVQ0475ZAE9TJV6/toolSets/create) page in your workspace. From there, we’ll add our Faker tool set.\n\nThe MCP settings in your tool set should look like this:\n\nSave the tool set, and you’re ready to use it in your agent!\n\n### Adding it to your variation\n\nHead back to the Agents → GLM page and assign your tool set to your variation. Once you’re on the agent page, find the “Add Assignment” button and search for the Faker Tools tool set you just created.\n\n### Watching GLM use the tools\n\nFollow the steps from earlier to give the agent a new objective with a prompt like this:\n\n```\nHello, I need a fake name generated for me.\n```\n\nThe new objective will be dispatched to the agent, and we’ll see it call the Faker Tools tool set to generate a fake name.\n\n## Wrapping up\n\nUsing open-weight models is not scary with tools like Modal on the market. Cadenya is a great way to quickly try these fast, cheap models with low risk, too.\n\n## Grow wherever AI goes next.\n\nStart shipping agents that are equipped to evolve.", "url": "https://wpnews.pro/news/using-modal-for-glm-flash-on-cadenya-s-agent-runtime", "canonical_source": "https://www.cadenya.com/handwritten/using-glm-on-cadenya", "published_at": "2026-09-12 12:55:12+00:00", "updated_at": "2026-09-12 13:11:18.979697+00:00", "lang": "en", "topics": ["ai-agents", "ai-products", "ai-tools", "large-language-models", "ai-infrastructure"], "entities": ["Cadenya", "Modal", "GLM 5.3 Flash", "Robert Ross", "Zhipu AI", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/using-modal-for-glm-flash-on-cadenya-s-agent-runtime", "markdown": "https://wpnews.pro/news/using-modal-for-glm-flash-on-cadenya-s-agent-runtime.md", "text": "https://wpnews.pro/news/using-modal-for-glm-flash-on-cadenya-s-agent-runtime.txt", "jsonld": "https://wpnews.pro/news/using-modal-for-glm-flash-on-cadenya-s-agent-runtime.jsonld"}}