# DSPy

URL: https://docs.hanzo.ai/docs/guides/integrations/dspy

> dspy.LM takes api_base through kwargs, forwarded to LiteLLM. Name the model in provider/name form.

`dspy.LM` takes **`api\_base`**. Note the spelling — it is not `base\_url`. The parameter is not in the explicit signature; it lands in `\*\*kwargs\`, which DSPy forwards to LiteLLM, and the API reference names it as an LM field.

```bash
pip install dspy
```

```python
import dspy

lm = dspy.LM(
    "openai/zen6",
    api_base="https://api.hanzo.ai/v1",
    api_key="sk-...",
    model_type="chat",
)
dspy.configure(lm=lm)

qa = dspy.Predict("question -> answer")
print(qa(question="What moves the tides?").answer)
```

Lands on `POST /v1/chat/completions`.

The `openai/` prefix is LiteLLM's provider form; the segment after it is the model id. `model_type` takes `chat`, `text` or `responses`, so `POST /v1/responses` is reachable from the same constructor.

## MCP

DSPy converts MCP tools rather than owning a client. `dspy.Tool.from_mcp_tool(client, tool)` turns each one into a `dspy.Tool` you hand to a module such as `dspy.ReAct`, so the server URL is configured on the MCP SDK client, not on any DSPy parameter.

```python
import dspy

tools = [dspy.Tool.from_mcp_tool(session, tool) for tool in (await session.list_tools()).tools]
react = dspy.ReAct("question -> answer", tools=tools)
```

`session` is a `ClientSession` from the MCP Python SDK, connected however that SDK connects — for `https://api.hanzo.ai/v1/mcp` that is its streamable HTTP client, with the bearer header set there.