Skip to main content
Pixeltable’s OpenRouter integration enables you to access multiple LLM providers through a unified API via OpenRouter.

​
Prerequisites

​
Important Notes

  • OpenRouter usage may incur costs based on the models you use and your usage volume.
  • Be mindful of sensitive data and consider security measures when integrating with external services.
First you’ll need to install required libraries and enter your OpenRouter API key. 
%pip install -qU pixeltable openai

import os
import getpass

if 'OPENROUTER_API_KEY' not in os.environ:
    os.environ['OPENROUTER_API_KEY'] = getpass.getpass('Enter your OpenRouter API key:')
Now let’s create a Pixeltable directory to hold the tables for our demo. 
import pixeltable as pxt

# Remove the 'openrouter_demo' directory and its contents, if it exists
pxt.drop_dir('openrouter_demo', force=True)
pxt.create_dir('openrouter_demo')

Connected to Pixeltable database at: postgresql+psycopg://postgres:@/pixeltable?host=/Users/asiegel/.pixeltable/pgdata
Created directory 'openrouter_demo'.

​
Chat Completions

Create a Table: In Pixeltable, create a table with columns to represent your input data and the columns where you want to store the results from OpenRouter. 
from pixeltable.functions import openrouter

# Create a table in Pixeltable and add a computed column that calls OpenRouter
t = pxt.create_table('openrouter_demo.chat', {'input': pxt.String})

messages = [{'role': 'user', 'content': t.input}]

t.add_computed_column(output=openrouter.chat_completions(
    messages=messages,
    model='anthropic/claude-3.5-sonnet',
    model_kwargs={
        # Optional dict with parameters compatible with the model
        'max_tokens': 300,
        'temperature': 0.7
    }
))

Created table 'chat'.
Added 0 column values with 0 errors.

No rows affected.

# Parse the response into a new column
t.add_computed_column(response=t.output.choices[0].message.content)

Added 0 column values with 0 errors.

No rows affected.

# Start a conversation
t.insert([
    {'input': 'How many species of felids have been classified?'},
    {'input': 'Can you make me a coffee?'}
])
t.select(t.input, t.response).head()

Inserting rows into `chat`: 2 rows [00:00, 166.89 rows/s]
Inserted 2 rows with 0 errors.
input response
How many species of felids have been classified? There are currently 40 recognized species of felids (members of the family Felidae), which includes all wild cats as well as domestic cats. These range from small cats like the rusty-spotted cat to large cats like tigers and lions. This classification can occasionally be updated as new research provides better understanding of cat taxonomy.
Can you make me a coffee? I cannot make you a coffee as I am an AI language model - I don't have physical form or ability to interact with the physical world. I can, however, give you instructions on how to make different types of coffee, recommend coffee recipes, or provide information about coffee in general. Would you like any of those instead?

​
Using Different Models

One of OpenRouter’s key benefits is easy access to models from multiple providers. Let’s create a table that compares responses from Anthropic Claude, OpenAI GPT-4, and Meta Llama. 
# Create a table to compare different models
compare_t = pxt.create_table('openrouter_demo.compare_models', {'prompt': pxt.String})

messages = [{'role': 'user', 'content': compare_t.prompt}]

# Add responses from different models
compare_t.add_computed_column(
    claude=openrouter.chat_completions(
        messages=messages,
        model='anthropic/claude-3.5-sonnet',
        model_kwargs={'max_tokens': 150}
    ).choices[0].message.content
)

compare_t.add_computed_column(
    gpt4=openrouter.chat_completions(
        messages=messages,
        model='openai/gpt-4o-mini',
        model_kwargs={'max_tokens': 150}
    ).choices[0].message.content
)

compare_t.add_computed_column(
    llama=openrouter.chat_completions(
        messages=messages,
        model='meta-llama/llama-3.1-8b-instruct',
        model_kwargs={'max_tokens': 150}
    ).choices[0].message.content
)


Created table 'compare_models'.
Added 0 column values with 0 errors.
Added 0 column values with 0 errors.
Added 0 column values with 0 errors.

No rows affected.

# Insert a prompt and compare responses
compare_t.insert([{'prompt': 'Explain quantum entanglement in one sentence.'}])
compare_t.select(compare_t.prompt, compare_t.claude, compare_t.gpt4, compare_t.llama).head()

Inserting rows into `compare_models`: 1 rows [00:00, 131.36 rows/s]
Inserted 1 row with 0 errors.
prompt claude gpt4 llama
Explain quantum entanglement in one sentence. Quantum entanglement is a phenomenon where two or more particles become so deeply connected that the quantum state of each particle cannot be described independently, even when separated by large distances. Quantum entanglement is a phenomenon in which two or more particles become interconnected in such a way that the state of one particle instantaneously influences the state of the other, regardless of the distance separating them. Quantum entanglement is a phenomenon in which two or more particles become interconnected in such a way that their properties, such as spin or polarization, are correlated, regardless of the distance between them.

​
Advanced Features: Provider Routing

OpenRouter allows you to specify provider preferences for fallback behavior and cost optimization. 
# Create a table with provider routing
routing_t = pxt.create_table('openrouter_demo.routing', {'input': pxt.String})

messages = [{'role': 'user', 'content': routing_t.input}]
routing_t.add_computed_column(
    output=openrouter.chat_completions(
        messages=messages,
        model='anthropic/claude-3.5-sonnet',
        model_kwargs={'max_tokens': 300},
        # Specify provider preferences
        provider={
            'order': ['Anthropic', 'OpenAI'],  # Try Anthropic first, then OpenAI
            'allow_fallbacks': True
        }
    )
)

routing_t.add_computed_column(response=routing_t.output.choices[0].message.content)

Created table 'routing'.
Added 0 column values with 0 errors.
Added 0 column values with 0 errors.

No rows affected.

routing_t.insert([{'input': 'What are the primary colors?'}])
routing_t.select(routing_t.input, routing_t.response).head()

Inserting rows into `routing`: 1 rows [00:00, 142.11 rows/s]
Inserted 1 row with 0 errors.
input response
What are the primary colors? The primary colors are: 1. Red 2. Blue 3. Yellow These are called primary colors because they cannot be created by mixing other colors together, and they can be combined to create all other colors. For example: - Red + Blue = Purple - Blue + Yellow = Green - Red + Yellow = Orange

​
Advanced Features: Context Window Optimization

OpenRouter supports transforms like ‘middle-out’ to optimize handling of long contexts. 
# Create a table with transforms for long context optimization
transform_t = pxt.create_table('openrouter_demo.transforms', {'long_context': pxt.String})

messages = [{'role': 'user', 'content': transform_t.long_context}]
transform_t.add_computed_column(
    output=openrouter.chat_completions(
        messages=messages,
        model='openai/gpt-4o-mini',
        model_kwargs={'max_tokens': 200},
        # Apply middle-out transform for better long context handling
        transforms=['middle-out']
    )
)

transform_t.add_computed_column(response=transform_t.output.choices[0].message.content)

Created table 'transforms'.
Added 0 column values with 0 errors.
Added 0 column values with 0 errors.

No rows affected.

# Example with longer context
long_text = """
Artificial intelligence has transformed many industries. Machine learning algorithms 
can now detect patterns in data that humans might miss. Deep learning has revolutionized 
computer vision and natural language processing. The future of AI looks promising with 
developments in areas like reinforcement learning and generative models.

Question: What are the main AI developments mentioned?
"""

transform_t.insert([{'long_context': long_text}])
transform_t.select(transform_t.response).head()


Inserting rows into `transforms`: 1 rows [00:00, 123.46 rows/s]
Inserted 1 row with 0 errors.
response
The main AI developments mentioned are: 1. Machine learning algorithms that detect patterns in data. 2. Deep learning, specifically in computer vision and natural language processing. 3. Advancements in reinforcement learning. 4. Developments in generative models.

​
Learn More

To learn more about advanced techniques like RAG operations in Pixeltable, check out the RAG Operations in Pixeltable tutorial. For more information about OpenRouter’s features and available models, visit: - OpenRouter Documentation - Available Models If you have any questions, don’t hesitate to reach out.