> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Custom model configurations

> Call saved model configurations through the LLM Gateway to reach custom endpoints and use them in fallback chains.

<Note>
  The LLM Gateway is in [beta](/langsmith/release-stages).
</Note>

[Model configurations](/langsmith/model-configurations) are named, reusable definitions that pair a provider and model with credentials and settings. The LLM Gateway can route a request through a saved configuration when you set the model ID to `custom/<name>`. Use a configuration to reach an endpoint that a provider-prefixed model ID cannot address, such as a custom OpenAI-compatible endpoint.

## Understand what the gateway uses

A bring-your-own-key gateway call normally targets a model with a provider-prefixed ID such as `openai/gpt-5.4-mini`. When the model ID is `custom/<name>`, the gateway reads the following from the saved configuration instead:

* **Provider and model**: The gateway sends the configuration's model name upstream, replacing the `custom/<name>` value in the request body.
* **API key secret**: The gateway authenticates to the provider with the workspace secret named in the configuration.
* **Connection settings**: The base URL, the OpenAI provider API (Chat Completions or Responses), and the Vertex AI project and location, where the provider uses them.

The gateway ignores generation parameters saved on the configuration, such as temperature, top P, and max output tokens. Pass these in each API request instead.

Workspace admins create configurations under **Settings** > **Model configurations**. For the steps, see [Create a configuration](/langsmith/model-configurations#create-a-configuration).

## Call a configuration through the gateway

Use `custom/<name>` as the model ID in any standard gateway request, replacing `<name>` with the configuration's exact name as shown in **Settings** > **Model configurations**:

<CodeGroup>
  ```bash Cloud theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  curl https://gateway.smith.langchain.com/v1/responses \
      -H "Authorization: Bearer $LANGSMITH_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"model":"custom/my-openai-config","input":"Hello!"}'
  ```

  ```bash BYOC theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  curl https://<data_plane_host>/gateway/v1/responses \
      -H "Authorization: Bearer $LANGSMITH_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"model":"custom/my-openai-config","input":"Hello!"}'
  ```
</CodeGroup>

The gateway looks up the configuration by name in the API key's workspace, including [organization-scoped configurations](/langsmith/model-configurations#organization-scoped-model-configurations), routes the request to the configured provider and endpoint, and returns the response in the [API format](/langsmith/llm-gateway-api-formats) the client used.

Saved configurations do not appear in the `GET /v1/models` list, so share configuration names with developers directly.

If a [model access policy](/langsmith/llm-gateway-model-access-policies#allow-saved-model-configurations) applies to the request, the policy must allow saved model configurations, or the gateway returns a `403` response.

## Use a configuration in a fallback chain

A [fallback chain](/langsmith/llm-gateway-fallbacks) can use a saved configuration in two places:

* **As the primary model**: Select the configuration as the chain's primary model. Requests to `custom/<name>` then fail over to the chain's backup models.
* **As a fallback candidate**: Add the configuration as one of the backup models. Requests to the chain's primary model ID can then fail over to the configuration's endpoint.

To give a Playground prompt its own fallback behavior, set the prompt's model to `custom/<name>` and attach a chain to that configuration. For the steps, see [Set fallbacks for a prompt](/langsmith/llm-gateway-fallbacks#set-fallbacks-for-a-prompt).

## See also

* [Manage model configurations](/langsmith/model-configurations): create, edit, and delete configurations; configure OAuth client credentials; manage organization-scoped configurations.
* [Model fallbacks](/langsmith/llm-gateway-fallbacks): retry failed requests against backup models and configurations.
* [API formats](/langsmith/llm-gateway-api-formats): supported request and response formats, model ID syntax, and translation behavior.

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to your agent of choice via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/llm-gateway-model-configurations.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>