--- title: "Databricks Agents" url: "/docs/a2a_databricks_agent" canonical_url: "https://docs.litellm.ai/docs/a2a_databricks_agent" type: "docs" last_updated: "2026-10-11" summary: "Register a Databricks ResponsesAgent as a LiteLLM agent and call it through /a2a/ or as model: a2a/ on /v1/chat/completions, /v1/responses, and /v1/messages." related: - "/docs/a2a_invoking_agents" - "/docs/a2a_agent_headers" --- # Databricks Agents > Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt Register a Databricks ResponsesAgent as a LiteLLM agent and call it through `/a2a/` or as `model: a2a/` on `/v1/chat/completions`, `/v1/responses`, and `/v1/messages`. | Feature | Supported | |---|---| | Agent type | `databricks_agent` | | Model Serving endpoints | ✅ | | Databricks Apps | ✅ | | Streaming | ✅ | | Auth | Personal access token, OAuth M2M service principal | ## How it works A Databricks ResponsesAgent speaks the OpenAI Responses API shape. LiteLLM flattens the chat messages to Responses `input` items, posts them to the agent, and maps the agent's `output` back to a chat completion or to an A2A message. Tool calls stay inside the agent, so none are mapped. ## Endpoint URLs `api_base` takes any of these shapes. The endpoint name goes in `model` only where the URL does not already name it. | `api_base` | `model` | What LiteLLM calls | |---|---|---| | `https://` or `https:///serving-endpoints` | required | `https:///serving-endpoints//invocations` | | `https:///serving-endpoints/` | ignored | `https:///serving-endpoints//invocations` | | `https:///serving-endpoints//invocations` | ignored | the URL as given | | `https:///serving-endpoints/responses` | required, sent as the body `model` | the URL as given | | `https://.databricksapps.com` | ignored | `https://.databricksapps.com/responses` | | `https://.databricksapps.com/` | ignored | the URL as given | A workspace or unified URL without a `model` answers 400 before any call is made. ## Authentication The agent's own credential wins over a client `Authorization` header. The order is the minted OAuth token, then the agent's `api_key` (a personal access token), then the `DATABRICKS_API_KEY` environment variable, then an OAuth M2M token minted from `DATABRICKS_CLIENT_ID` and `DATABRICKS_CLIENT_SECRET`. A client `Authorization` header is used only when the agent has none of these. ### OAuth M2M (recommended) Databricks Apps accept OAuth tokens only, and OAuth M2M is the recommended production auth for Model Serving too. Set the service principal's `client_id` and `client_secret` on the agent. `workspace_url` defaults to the `api_base` origin for Model Serving. A Databricks App host is never a token endpoint, so an App agent must set `workspace_url`, and the client secret is never posted to the App host. The minted token is cached until shortly before it expires and refreshed on the next call. ### Personal access token Set `api_key` to a PAT, or set `DATABRICKS_API_KEY` in the proxy's environment. Databricks Apps reject PATs. ### Environment service principal When the proxy's environment sets `DATABRICKS_CLIENT_ID` and `DATABRICKS_CLIENT_SECRET`, a `databricks_agent` with no `api_key` mints an OAuth M2M token from them on each call, the same way the `databricks` model provider does. The token endpoint is the `DATABRICKS_HOST` workspace when set, else the `api_base` origin. An App `api_base` with no `DATABRICKS_HOST` answers 400 naming `DATABRICKS_HOST`. ## Register the agent **UI** 1. Go to **Agentic** > **Agents** in the LiteLLM dashboard. 2. Click **Add New Agent** and pick **Databricks Agent**. 3. Enter the agent name, the `api_base`, and the `model` (the serving endpoint name) where the URL does not already name it. 4. Fill in either a personal access token or the service principal's `client_id`, `client_secret`, and, for an App, `workspace_url`. 5. Save the agent. **config.yaml** ```yaml title="config.yaml" agents: - agent_name: dbx-serving agent_card_params: name: "Databricks ResponsesAgent on Model Serving" litellm_params: custom_llm_provider: databricks_agent model: my-responses-agent api_base: https://adb-1234567890123456.7.azuredatabricks.net client_id: os.environ/DATABRICKS_CLIENT_ID client_secret: os.environ/DATABRICKS_CLIENT_SECRET - agent_name: dbx-app agent_card_params: name: "Databricks App ResponsesAgent" litellm_params: custom_llm_provider: databricks_agent api_base: https://my-agent-app-1234567890123456.7.azure.databricksapps.com client_id: os.environ/DATABRICKS_CLIENT_ID client_secret: os.environ/DATABRICKS_CLIENT_SECRET workspace_url: https://adb-1234567890123456.7.azuredatabricks.net ``` **REST API** ```bash curl -X POST http://localhost:4000/v1/agents \ -H "Authorization: Bearer sk-admin" \ -H "Content-Type: application/json" \ -d '{ "agent_name": "dbx-serving", "agent_card_params": {"name": "Databricks ResponsesAgent on Model Serving"}, "litellm_params": { "custom_llm_provider": "databricks_agent", "model": "my-responses-agent", "api_base": "https://adb-1234567890123456.7.azuredatabricks.net", "api_key": "os.environ/DATABRICKS_API_KEY" } }' ``` ## Call the agent **Chat completions** ```bash curl http://localhost:4000/v1/chat/completions \ -H "Authorization: Bearer sk-client-key" \ -H "Content-Type: application/json" \ -d '{ "model": "a2a/dbx-serving", "messages": [{"role": "user", "content": "Reply with exactly: pong"}], "custom_inputs": {"tenant": "t-1"} }' ``` `stream: true` streams the agent's `output_text` deltas as chat chunks. `/v1/responses` and `/v1/messages` take the same `model: a2a/`. **A2A** ```bash curl http://localhost:4000/a2a/dbx-serving \ -H "Authorization: Bearer sk-client-key" \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": "1", "method": "message/send", "params": { "message": { "role": "user", "messageId": "1", "parts": [{"kind": "text", "text": "Reply with exactly: pong"}] } } }' ``` `message/stream` streams a task, a working status, an artifact with the reply, and a completed status. ## Request parameters `custom_inputs`, `context`, and `databricks_options` pass through to the agent as sent. Other OpenAI parameters such as `temperature` answer 400 unless `drop_params` is set, in which case they are dropped. Messages are sent as text. Image, file, and audio content parts, assistant `tool_calls`, and `tool` or `function` messages answer 400 naming them. Under `drop_params` they are dropped, and a message with nothing left is left out of the request. The agent's `custom_outputs`, when present, come back under `provider_specific_fields` on the chat message. A reply with no `usage` has its tokens counted locally. ## Related - [Invoking A2A Agents](a2a_invoking_agents) - [A2A Agent Authentication Headers](a2a_agent_headers) - [Databricks model provider](/docs/providers/databricks) ## Related pages - [Invoking A2A Agents](https://docs.litellm.ai/docs/a2a_invoking_agents.md) - [A2A Agent Authentication Headers](https://docs.litellm.ai/docs/a2a_agent_headers.md)