This integration is for the Keywords AI gateway. If you only need to log LLM calls and responses, use the Logging API.

Keywords AI provides a robust and flexible LLM proxy with 250+ LLMs. You can use Keywords AI with OpenAI SDK by just passing the base_url and api_key to the OpenAI SDK.

With this integration, your LLM request will go through the Keywords AI gateway, and the requests will be automatically logged to Keywords AI.

Integration examples

from openai import OpenAI

client = OpenAI(
    base_url="https://api.keywordsai.co/api/",
    api_key=YOUR_KEYWORDSAI_API_KEY,
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role":"user", "content":"Tell me a long story"}],
)

Supported parameters

OpenAI parameters

We support all the OpenAI parameters. You can pass them directly in the request body.

You can pass Keywords AI parameters in the extra_body parameter.

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True,
)

Keywords AI parameters

Keywords AI parameters can be passed differently depending on your programming language:

You can pass Keywords AI parameters in the extra_body parameter.

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Tell me a story"}],
    extra_body={"customer_identifier": "test_user_1"}
)

These parameters will take precedence over the OpenAI parameters if they are conflicting.

Call Azure OpenAI with OpenAI SDK

To call Azure OpenAI models, instead of using azure OpenAI’s client, the easier way is to use the OpenAI client.

from openai import AsyncOpenAI

azureaclient = AsyncOpenAI(
    api_key=KEYWORDSAI_API_KEY,
    base_url="https://api.keywordsai.co/api"
)

response = await azureaclient.chat.completions.create(**kwargs)

Then You can upload your Azure credentials to Keywords AI platform to use those models. Check out our Providers integration.