> ## Documentation Index > Fetch the complete documentation index at: https://ngrok.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Connect a coding agent to custom models > Point OpenCode, Zed, Pi, Cursor, or another OpenAI-compatible coding agent at the AI Gateway to reach a model you run on your own machine. Some coding agents let you replace their built-in model with any OpenAI-compatible endpoint. Point one at `https://gateway.ngrok.ai/v1` and it can call a self-hosted model on your own machine, a hosted GPU, or anywhere else it can run. ## What you'll need * The [ngrok agent](https://ngrok.com/download) installed on the machine where your model runs * An [access key](/docs/ai-gateway/concepts/access-keys) from [app.ngrok.ai](https://app.ngrok.ai) * A model server such as [Ollama](/docs/ai-gateway/custom-providers/ollama), [LM Studio](/docs/ai-gateway/custom-providers/lm-studio), or [vLLM](/docs/ai-gateway/custom-providers/vllm) ## Getting started Expose your model server with an ngrok internal endpoint. For a server listening on port `11434`: ```bash theme={null} ngrok http 11434 --url https://my-ollama.internal ``` Create a [custom provider](/docs/ai-gateway/concepts/custom-providers) in [app.ngrok.ai](https://app.ngrok.ai): 1. Go to **Providers** and open the **Custom** tab. 2. Select **Add provider**. 3. Enter a provider ID, the base URL, the API format, and your model IDs. 4. Add a provider key if the upstream requires authentication. For the full setup, including the API method and URL requirements, see [Use a model you run yourself](/docs/ai-gateway/guides/use-a-model-you-run-yourself) or the specific [Ollama](/docs/ai-gateway/custom-providers/ollama), [LM Studio](/docs/ai-gateway/custom-providers/lm-studio), and [vLLM](/docs/ai-gateway/custom-providers/vllm) guides. Every agent below needs the same three values: | Value | What to enter | | -------- | ------------------------------------------------------------------------- | | Base URL | `https://gateway.ngrok.ai/v1` | | API key | Your [access key](https://app.ngrok.ai/keys), such as `ng-xxxxx-g1-xxxxx` | | Model | Your `provider:model` name, such as `ollama:llama3.2` | [OpenCode](https://opencode.ai) is a terminal coding agent. Add the gateway as a provider in `~/.config/opencode/opencode.json`, or in an `opencode.json` beside your project: ```json theme={null} { "$schema": "https://opencode.ai/config.json", "provider": { "ngrok": { "npm": "@ai-sdk/openai-compatible", "name": "ngrok AI Gateway", "options": { "baseURL": "https://gateway.ngrok.ai/v1", "apiKey": "ng-xxxxx-g1-xxxxx" }, "models": { "ollama:llama3.2": { "name": "Llama 3.2 (via ngrok)" } } } } } ``` Replace these required fields: * `apiKey` with your ngrok.ai access key * Keys in the `models` field with your full `provider:model` name and display-friendly name Then test it with a prompt, replacing `ngrok/ollama:llama3.2` with your model: ```bash theme={null} opencode run -m "ngrok/ollama:llama3.2" "Explain quantum entanglement like I'm 10." ``` [Zed](https://zed.dev) is a code editor with a built-in agent panel. Add the provider to your `settings.json`: ```json theme={null} { "language_models": { "openai_compatible": { "ngrok": { "api_url": "https://gateway.ngrok.ai/v1", "available_models": [ { "name": "ollama:llama3.2", "max_tokens": 131072 } ] } } } } ``` Replace these required fields: * `name` with your `provider:model` name * `max_tokens` with your model's context window Next, add your ngrok.ai access key through the Zed UI. Open the command palette, run **agent: open settings**, select **LLM Providers**, then **Configure**, find **ngrok** in the provider list, paste your access key, and hit **Enter**. Create a new Zed Agent Thread, pick your custom model from the selector at the bottom of the agent panel's message editor, and test it: Explain quantum entanglement like I'm 10. [Pi](https://pi.dev) is a terminal coding agent. Add the gateway as a provider in `~/.pi/agent/models.json`: ```json theme={null} { "providers": { "ngrok": { "baseUrl": "https://gateway.ngrok.ai/v1", "apiKey": "ng-xxxxx-g1-xxxxx", "api": "openai-completions", "models": [ { "id": "ollama:llama3.2" } ] } } } ``` Replace these required fields: * `apiKey` with your ngrok.ai access key * `id` with your full `provider:model` name `id` is the only field a model entry needs, though you can add `name`, `contextWindow`, and `maxTokens` to label it and track context accurately. Then test it with a prompt: ```bash theme={null} pi --provider ngrok --model "ollama:llama3.2" -p "Explain quantum entanglement like I'm 10." ``` [Cursor](https://cursor.com) is a code editor with a built-in agent. It reaches custom models by overriding the base URL of its OpenAI provider, so the gateway stands in for OpenAI. This needs a paid Cursor plan. Free plans can only use Cursor's **Auto** model and can't select a named model, which is what a model you add yourself is. Open **Cursor Settings**, go to **Models**, and expand **API Keys**: 1. Turn on **OpenAI API Key** and paste your ngrok.ai access key. The field is labeled OpenAI, but Cursor sends the key to whatever endpoint you configure below. 2. Turn on **Override OpenAI Base URL** and enter `https://gateway.ngrok.ai/v1`. Keep the `/v1` suffix: Cursor appends `/chat/completions` to whatever you enter. 3. Select **+ Add model**, enter your full `provider:model` name, such as `ollama:llama3.2`, and enable it. 4. Select **Verify** to confirm the gateway answers. Pick your model in the chat model selector and test it: Explain quantum entanglement like I'm 10. The base URL override is global. While it's on, Cursor routes its other OpenAI-model traffic to the gateway too, which fails for models your access key can't reach. Turn the override off to go back to Cursor's own models. Expect chat, not the whole editor. Three Cursor behaviors limit how far a custom model reaches: * Tab completion always uses Cursor's built-in models. It never reaches your endpoint. * Agent and Edit also rely on Cursor's own models, so Cursor may refuse them while a custom API key is set and ask you to disable the key. * Where agent runs do work, Cursor's tool definitions over an overridden base URL aren't strictly OpenAI-shaped, so tool calls can fail against a self-hosted model even when plain chat succeeds. Want us to add instructions for a specific coding agent? Log in to [app.ngrok.ai](https://app.ngrok.ai), click **Give feedback**, and let us know what you'd like to see. Any tool that accepts an OpenAI base URL and key theoretically works the same way. Set the base URL to `https://gateway.ngrok.ai/v1`, the key to your access key, and the model to your `provider:model` name. Name the model yourself rather than picking it from a list. A tool that populates its model picker by calling the gateway won't find your models. The gateway serves these endpoints, so tools that use the Responses API or the Anthropic Messages API work too: | Endpoint | Format | | ---------------------- | --------- | | `/v1/chat/completions` | OpenAI | | `/v1/responses` | OpenAI | | `/v1/messages` | Anthropic | `/v1/messages` only reaches providers that support the Anthropic Messages surface. Ollama, LM Studio, and vLLM expose the OpenAI surface, so send requests for a model you run yourself to `/v1/chat/completions` or `/v1/responses`. For SDK-level examples, see [Use with other SDKs](/docs/ai-gateway/sdks/other). Double-check that your self-hosted model served the request with AI Gateway [observability](/docs/ai-gateway/observability) in [app.ngrok.ai](https://app.ngrok.ai). ## Next steps * [Restrict providers and models](/docs/ai-gateway/guides/restrict-providers-and-models): Scope what an access key can call * [Observability](/docs/ai-gateway/observability): See which model served each request * [Configure fallback models](/docs/ai-gateway/guides/configure-fallback-models): Try another model when the first one fails