### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### The Feature

Add an opt-in way for the LiteLLM Proxy/Gateway `GET /models` and `GET /v1/models` endpoints to include pricing metadata for each model.

For example:

```http GET /v1/models ```

```json { "data": [ { "id": "gpt-4o", "object": "model", "created": 1677610602, "owned_by": "openai", "pricing": { "prompt": "0.0000025", "completion": "0.0000100" } } ], "object": "list" } ```

The pricing should reflect the effective Gateway configuration, including LiteLLM's model cost map and deployment-specific custom pricing from `model_info`/`litellm_params`.

[OpenRouter's `GET /api/v1/models`](https://openrouter.ai/api/v1/models) already returns a `pricing` object alongside each model. Supporting a similar optional shape would make LiteLLM model discovery more useful while remaining familiar to existing agent and routing integrations.

Suggested behavior:

- Return pricing only for models accessible to the requesting API key/team. - Include at least prompt/input and completion/output token prices.…