​
Deployments

PureRouter is a completely independent product from PureCPP. You can use PureRouter without needing PureCPP and vice versa.
In addition to automatic routing through profiles, PureRouter allows you to directly access specific models through their deployment IDs. This is useful when you need a particular model for a specific use case.

​
Before You Start

To use deployments, you will need:

​
Accessing Deployments

To access a specific deployment, you need its unique ID: 
from purerouter import PureRouter
from purerouter.types import InvokeRequest

client = PureRouter(router_key="your-api-key-here")

# Direct call to a specific model by ID
response = client.deployments.invoke(
    "ca10db2f-364e-55dc-9d0f-b56e36f1140f",  # Deployment ID
    InvokeRequest(
        messages=[{"role": "user", "content": "Hello, how can I help?"}],
        parameters={"temperature": 0.7}
    )
)
print(response)

​
Getting Deployment IDs

You can get the deployment IDs available for your account through the PureAI platform or via API: 
# List all available deployments
deployments = client.deployments.list()

for deployment in deployments:
    print(f"ID: {deployment.id}")
    print(f"Name: {deployment.name}")
    print(f"Model: {deployment.model}")
    print(f"Status: {deployment.status}")
    print("---")

​
Invocation Parameters

When invoking a specific deployment, you can configure various parameters: 
response = client.deployments.invoke(
    "deployment-id",
    InvokeRequest(
        messages=[
            {"role": "system", "content": "You are a helpful and friendly assistant."},
            {"role": "user", "content": "Explain the concept of machine learning."}
        ],
        parameters={
            "temperature": 0.7,  # Controls randomness (0.0 to 1.0)
            "max_tokens": 500,  # Limits response size
            "top_p": 0.95,      # Nucleus sampling
            "frequency_penalty": 0.0,  # Penalty for token repetition
            "presence_penalty": 0.0    # Penalty for topic repetition
        }
    )
)

​
Response Streaming

To get real-time responses (streaming): 
# Streaming response from a specific deployment
for chunk in client.deployments.invoke_stream(
    "deployment-id",
    InvokeRequest(
        messages=[{"role": "user", "content": "Tell a long story"}],
        parameters={"temperature": 0.8}
    )
):
    print(chunk.choices[0].delta.content, end="", flush=True)

​
Use Cases for Direct Deployments

​
Practical Example: Fallback System

def process_query_with_fallback(query):
    # Try first with the preferred model
    try:
        response = client.deployments.invoke(
            "primary-model-id",
            InvokeRequest(
                messages=[{"role": "user", "content": query}],
                parameters={"temperature": 0.7}
            )
        )
        return response
    except Exception as e:
        print(f"Error in primary model: {e}")

        # Fallback to an alternative model
        try:
            response = client.deployments.invoke(
                "fallback-model-id",
                InvokeRequest(
                    messages=[{"role": "user", "content": query}],
                    parameters={"temperature": 0.7}
                )
            )
            return response
        except Exception as e:
            print(f"Error in fallback model: {e}")

            # Last resort: use automatic routing
            return client.router.infer(InferRequest(
                prompt=query,
                profile="balanced"
            ))

​
Next Steps

Python SDK

Learn to use the PureRouter Python SDK

Routing Profiles

Learn more about economy, balanced, and quality profiles

API Reference

Check the complete API documentation