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

# LLMSwitcher

> Dynamically switch between different LLM services with support for ad-hoc inference and unified function registration

## Overview

`LLMSwitcher` is a specialized version of `ServiceSwitcher` designed specifically for managing multiple LLM services. Beyond basic service switching, it provides convenient methods for running ad-hoc inferences and registering function handlers across all LLMs simultaneously.

This is particularly useful when you need to switch between different LLM providers based on task complexity, cost optimization, or specific model capabilities while maintaining a consistent function calling interface.

## Constructor

```python theme={null}
from pipecat.pipeline.llm_switcher import LLMSwitcher

# Uses ServiceSwitcherStrategyManual by default
switcher = LLMSwitcher(llms=[openai_service, gemini_service])
```

<ParamField path="llms" type="List[LLMService]" required>
  List of LLM service instances to switch between.
</ParamField>

<ParamField path="strategy_type" type="Type[ServiceSwitcherStrategy]" default="ServiceSwitcherStrategyManual">
  The strategy class to use for switching logic. Pass the class itself, not an
  instance. Defaults to `ServiceSwitcherStrategyManual`.
</ParamField>

## Properties

<ParamField path="llms" type="List[LLMService]">
  The list of LLM services managed by this switcher.
</ParamField>

<ParamField path="active_llm" type="LLMService | None">
  The currently active LLM service, or None if no LLMs are configured.
</ParamField>

## Methods

### run\_inference()

Run a one-shot inference with the currently active LLM, outside of the normal pipeline flow.

```python theme={null}
result = await llm_switcher.run_inference(
    context=llm_context,
    max_tokens=1000,
    system_instruction="You are a helpful assistant."
)
```

<ParamField path="context" type="LLMContext" required>
  The LLM context containing conversation history and messages.
</ParamField>

<ParamField path="**kwargs" type="Any">
  Additional arguments forwarded to the active LLM's `run_inference` method.
  Common options include `max_tokens` (maximum tokens to generate) and
  `system_instruction` (override the system prompt for this inference).
</ParamField>

**Returns**: `str | None` - The LLM's response as a string, or None if no LLM is active.

### register\_function()

Register a function handler with all LLMs in the switcher, regardless of which is currently active.

```python theme={null}
llm_switcher.register_function(
    function_name="get_weather",
    handler=handle_weather,
    cancel_on_interruption=True
)
```

<ParamField path="function_name" type="str | None" required>
  The name of the function to handle. Use None for a catch-all handler that
  processes all function calls.
</ParamField>

<ParamField path="handler" type="Callable" required>
  The async function handler. Should accept a single `FunctionCallParams`
  parameter.
</ParamField>

<ParamField path="cancel_on_interruption" type="bool" default="True">
  Whether to cancel this function call when a user interruption occurs. When
  `False`, the call is treated as asynchronous: the LLM continues the
  conversation immediately without waiting for the result, and the result is
  injected later via a developer message.
</ParamField>

<ParamField path="timeout_secs" type="float | None" default="None">
  Optional per-tool timeout in seconds. Overrides the global
  `function_call_timeout_secs` for this specific function.
</ParamField>

### register\_direct\_function()

Register a direct function handler with all LLMs in the switcher, regardless of which is currently active. Direct functions provide more control over function call execution.

```python theme={null}
llm_switcher.register_direct_function(
    handler=my_direct_function,
    cancel_on_interruption=True,
    timeout_secs=30.0
)
```

<ParamField path="handler" type="DirectFunction" required>
  The direct function to register. Must follow the DirectFunction protocol.
</ParamField>

<ParamField path="cancel_on_interruption" type="bool" default="True">
  Whether to cancel this function call when a user interruption occurs. When
  `False`, the call is treated as asynchronous: the LLM continues the
  conversation immediately without waiting for the result, and the result is
  injected later via a developer message.
</ParamField>

<ParamField path="timeout_secs" type="float | None" default="None">
  Optional per-tool timeout in seconds. Overrides the global
  `function_call_timeout_secs` for this specific function.
</ParamField>

## Usage Examples

### Basic LLM Switching

```python theme={null}
from pipecat.pipeline.llm_switcher import LLMSwitcher
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.frames.frames import ManuallySwitchServiceFrame

# Create LLM services
openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
gemini = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))

# Create switcher (uses ServiceSwitcherStrategyManual by default)
llm_switcher = LLMSwitcher(llms=[openai, gemini])

# Use in pipeline
pipeline = Pipeline([
    transport.input(),
    stt,
    context_aggregator.user(),
    llm_switcher,
    tts,
    transport.output(),
    context_aggregator.assistant()
])

# Switch to cheaper model for simple tasks
await task.queue_frame(ManuallySwitchServiceFrame(service=gpt35))
```