Adding a custom LLM provider

Use this when the provider isn’t in the catalog: Azure AI Foundry, LiteLLM, vLLM, or an internal gateway. You add the endpoint and key once in OpenWork Cloud, and it syncs to members’ desktop apps. Custom endpoints are legacy providers, so the key is synced to members’ apps and there’s no usage tracking. If your provider is in the catalog, an AI Gateway provider keeps the key on the server instead. See Adding a managed LLM provider for how the two compare.

Create the custom provider

In OpenWork Cloud, open AI Gateway › AI Providers.
Scroll to Legacy Providers and click Add legacy provider.
Switch to Custom provider.
Paste the shared key into API key / credential.
Enter the Base URL of the OpenAI-compatible endpoint. It usually ends in /v1. For Azure AI Foundry it looks like https://my-resource.openai.azure.com/openai/v1.
OpenWork checks the endpoint and lists the models it serves. Pick the ones to share. If a model is missing, click My model isn’t listed — enter IDs manually and type the IDs in Model IDs, one per line. On Azure AI Foundry, these are your deployment names.
Enter a short Provider ID, such as azure-foundry. Or click Rename next to Name and type a name, and the Provider ID fills in from it. If you don’t rename it, the name is based on the endpoint, for example my-resource.openai.azure.com — key 1.
Under Who can use it, keep Everyone in (your organization name), or pick specific Teams and People.
Click Create Provider.

The Custom provider form: Provider ID, API key / credential, Base URL, and Model IDs

You don’t need to write JSON for an OpenAI-compatible endpoint. Once saved, the provider page shows its configuration, whether the key is saved, and the models you shared:

Acme LLM Gateway provider detail: Credential saved, provider ID, API base, and two selected models

Advanced: raw JSON config

If the provider needs more than the form covers (a different AI SDK package, per-model limits or modalities, custom options), click Advanced: edit as JSON and paste a models.dev-style definition into Custom provider JSON / JSONC. Click Use the guided form instead to go back. The JSON must include id, name, npm, env, and models; api is optional, but most OpenAI-compatible providers use it. The editor requires valid JSON, at least one environment variable, and at least one model.

{
  "id": "custom-provider",
  "name": "Custom Provider",
  "npm": "@ai-sdk/openai-compatible",
  "env": [
    "CUSTOM_PROVIDER_API_KEY"
  ],
  "doc": "https://example.com/docs/models",
  "api": "https://api.example.com/v1",
  "models": [
    {
      "id": "custom-provider/example-model",
      "name": "Example Model",
      "attachment": false,
      "reasoning": false,
      "tool_call": true,
      "structured_output": true,
      "temperature": true,
      "release_date": "2026-01-01",
      "last_updated": "2026-01-01",
      "open_weights": false,
      "limit": {
        "context": 128000,
        "input": 128000,
        "output": 8192
      },
      "modalities": {
        "input": [
          "text"
        ],
        "output": [
          "text"
        ]
      }
    }
  ]
}

What members see

Members don’t import anything. Their desktop app syncs the provider automatically, and its models show up in the model picker. Members can check status in Settings › AI Providers › Cloud providers. See What members see.

Functional example: an LLM gateway (Infron)

An LLM gateway is one OpenAI-compatible endpoint that fans out to many model providers. If you want to run the routing yourself, LiteLLM is a good starting point. Infron is the hosted option: one API key gets you every model in its marketplace with automatic provider fallbacks and a single invoice, so adding a new LLM to OpenWork is just another entry under models. Grab a key from the API Keys dashboard. If you don’t have an account yet, sign up at infron.ai/login and their quickstart walks you through your first request. Add a legacy provider, switch to Custom provider, and paste the key into API key / credential. Then click Advanced: edit as JSON and use this JSON:

{
  "id": "infron",
  "name": "Infron",
  "npm": "@ai-sdk/openai-compatible",
  "env": [
    "INFRON_API_KEY"
  ],
  "doc": "https://infron.ai/docs/frameworks-and-integrations/openwork",
  "api": "https://llm.onerouter.pro/v1",
  "models": [
    {
      "id": "deepseek/deepseek-v3.2",
      "name": "DeepSeek V3.2",
      "attachment": false,
      "reasoning": true,
      "tool_call": true,
      "structured_output": true,
      "temperature": true,
      "release_date": "2025-09-29",
      "last_updated": "2025-09-29",
      "open_weights": true,
      "limit": {
        "context": 128000,
        "input": 128000,
        "output": 8192
      },
      "modalities": {
        "input": ["text"],
        "output": ["text"]
      }
    }
  ]
}

Once synced, Infron models show up in the Chat model picker alongside everything else:

DeepSeek V3.2 via Infron in the OpenWork Chat model picker

Pick the model and it’s live in the session footer:

Infron · DeepSeek V3.2 selected in an OpenWork session

Add more entries under models to expose other routes the gateway supports (e.g. openai/gpt-5.4, google/gemini-2.5-flash).

When to use a cloud provider

Use a cloud provider when a whole org or team should share the setup. For your own computer only, add the provider in the desktop app instead.

Overview

Providers for your org

Usage and cost

Adding a custom LLM provider

Create the custom provider

Advanced: raw JSON config

What members see

Functional example: an LLM gateway (Infron)

When to use a cloud provider

​Create the custom provider

​Advanced: raw JSON config

​What members see

​Functional example: an LLM gateway (Infron)

​When to use a cloud provider

Create the custom provider

Advanced: raw JSON config

What members see

Functional example: an LLM gateway (Infron)

When to use a cloud provider