Together Code Interpreter

Execute LLM-generated code seamlessly with a simple API call.

Fast, secure code execution for LLM-generated code 

Together Code Interpreter allows you to execute LLM-generated Python code securely and feed the output back to the LLM for richer responses.

Build agentic workflows
Build coding agents that can run code to make decisions by calling APIs, processing data & performing calculations.
Data analysis & visualization
Analyze datasets to provide on-the-fly insights and visualizations like charts and graphs.
Reinforced learning
Bring code execution into interactive RL environments with real-time feedback, pass/fail signals, and easy scaling.

"Together Code Interpreter has dramatically accelerated our RL post-training cycles, enabling us to reliably scale to over 100 concurrent coding sandboxes and run thousands of code evaluations per minute. Its reliable and scalable infrastructure has proven invaluable."

‍

- Michael Luo & Sijun Tan, Project lead at Agentica

Configure powerful workflows with our Python library

Seamlessly execute Python code in a sandboxed environment.

Create a session

Create a Together Code Interpreter session that you can use to execute code. Each session is billed at $0.03/session.

code_interpreter = client.code_interpreter

Execute Python code in an active session

Execute code in a secure sandboxed environment, install Python libraries, upload files, and conduct fully fledged data analysis experiments.

# Simple print statement
print("Example 1: Simple print")
response = code_interpreter.run(
    code='print("Hello from Together!")',
    language="python"
)
print(f"Status: {response.data.status}")
for output in response.data.outputs:
    print(f"{output.type}: {output.data}")
if response.data.errors:
    print(f"Errors: {response.data.errors}")
print("\n")

Maintain the state between runs

The session_id can be used to access a previously initialized session. All packages, variables and memory will be retained.

session_id = response1.data.session_id

response2 = code_interpreter.run(
    code='print(f"The value of x is {x}")',
    language="python",
    session_id=session_id
)

for output in response2.data.outputs:
    print(f"{output.type}: {output.data}")
if response2.data.errors:
    print(f"Errors: {response2.data.errors}")
print("\n")

Read our cookbook

Bring Code Execution to Your AI Applications

Get started

Together Code Interpreter

Fast, secure code execution for LLM-generated code

Build agentic workflows

Data analysis & visualization

Reinforced learning

Configure powerful workflows with our Python library

Create a session

Execute Python code in an active session

Maintain the state between runs

Bring Code Execution to Your AI Applications

Subscribe to newsletter

Fast, secure code execution for LLM-generated code 