Requesty

Use Requesty AI gateway with Agno agents.

v2.1.0

Requesty AI is an LLM gateway with AI governance, providing unified access to various language models with built-in governance and monitoring capabilities.

Learn more about Requesty's features at requesty.ai.

Authentication

Set your REQUESTY_API_KEY environment variable. Get your key from Requesty.

export REQUESTY_API_KEY=***

Example

Install the openai package:

uv pip install -U agno openai

Use Requesty with your Agent:

from agno.agent import Agent
from agno.models.requesty import Requesty

agent = Agent(model=Requesty(id="openai/gpt-4o"), markdown=True)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story")
View more examples here.

Params

ParameterTypeDefaultDescription
idstr"openai/gpt-4.1"The id of the model to use through Requesty
namestr"Requesty"The name of the model
providerstr"Requesty"The provider of the model
api_keyOptional[str]NoneThe API key for Requesty (defaults to REQUESTY_API_KEY env var)
base_urlstr"https://router.requesty.ai/v1"The base URL for the Requesty API
max_tokensint1024The maximum number of tokens to generate

Requesty also supports the params of OpenAI.