Skip to main content
Large language models give agents the ability to make autonomous decisions. The Autonomy Computer provides a Model Gateway that gives your apps access to a wide range of models from different providers, each optimized for different use cases and cost profiles. You specify which model an agent should use by passing the model argument to Agent.start():
images/main/main.py
from autonomy import Agent, Model, Node


async def main(node):
  await Agent.start(
    node=node,
    name="henry",
    instructions="You are Henry, an expert legal assistant",
    model=Model("claude-sonnet-4-v1")
  )


Node.start(main)
You can easily switch models by changing the model name in your Model() constructor.

​
Supported Models

Autonomy supports a wide range of models from different providers:
ModelProviderDescription
claude-opus-4-v1AnthropicMost capable model for complex tasks
claude-sonnet-4-v1AnthropicBalanced performance and cost
nova-premier-v1AmazonHigh-performance model from AWS
deepseek-r1DeepSeekAdvanced reasoning capabilities
nova-pro-v1AmazonProfessional-grade AWS model
llama4-maverickMetaHigh-performance Llama 4 variant
llama4-scoutMetaEfficient Llama 4 variant
nova-lite-v1AmazonLightweight and cost-effective AWS model
nova-micro-v1AmazonUltra-lightweight, most cost-effective option
For detailed pricing information for each model, see the Pricing page.

​
Parameters

The Model() constructor accepts additional parameters that control the model’s behavior.
  • temperature: The sampling temperature to use, between 0 and 2. Higher values like 0.8 produce more random outputs, while lower values like 0.2 make outputs more focused and deterministic.
  • top_p: An alternative to sampling with temperature. It instructs the model to consider the results of the tokens with top_p probability. For example, 0.1 means only the tokens comprising the top 10% probability mass are considered.
images/main/main.py
from autonomy import Agent, Model, Node


async def main(node):
  # Use a lower temperature for more focused responses
  await Agent.start(
    node=node,
    name="analyst",
    instructions="You are a financial analyst",
    model=Model("claude-sonnet-4-v1", temperature=0.2)
  )


Node.start(main)

​
Invoke Models Directly

For simple use cases, you can also invoke models directly. This is useful when you need to make one-off completions without the full features of an agent.
images/main/main.py
from autonomy import Model, Node, SystemMessage, UserMessage


async def main(node):
  model = Model("claude-sonnet-4-v1")

  response = model.complete_chat([
    SystemMessage("You are a helpful assistant."),
    UserMessage("Explain gravity in simple terms")
  ])
  
  print(response)


Node.start(main)

​
Streaming Responses

You can also stream responses from models by setting stream=True:
images/main/main.py
from autonomy import Model, Node, SystemMessage, UserMessage


async def main(node):
  model = Model("claude-sonnet-4-v1")

  streaming_response = model.complete_chat([
      SystemMessage("You are a helpful assistant."),
      UserMessage("Explain gravity")
  ], stream=True)

  async for chunk in streaming_response:
    if hasattr(chunk, "choices") and chunk.choices and chunk.choices[0].delta.content:
      content = chunk.choices[0].delta.content
      print(content, end="")


Node.start(main)