/interactions

LiteLLM Python SDK Usage

Quick Start

from litellm import create_interaction

os.environ["GEMINI_API_KEY"] = "your-api-key"

response = create_interaction(
    model="gemini/gemini-2.5-flash",
    input="Tell me a short joke about programming."
)

print(response.outputs[-1].text)

Async Usage

from litellm import acreate_interaction

os.environ["GEMINI_API_KEY"] = "your-api-key"

async def main():
    response = await acreate_interaction(
        model="gemini/gemini-2.5-flash",
        input="Tell me a short joke about programming."
    )
    print(response.outputs[-1].text)

asyncio.run(main())

Streaming

from litellm import create_interaction

os.environ["GEMINI_API_KEY"] = "your-api-key"

response = create_interaction(
    model="gemini/gemini-2.5-flash",
    input="Write a 3 paragraph story about a robot.",
    stream=True
)

for chunk in response:
    print(chunk)

LiteLLM AI Gateway (Proxy) Usage

Setup

Add this to your litellm proxy config.yaml:

model_list:
  - model_name: gemini-flash
    litellm_params:
      model: gemini/gemini-2.5-flash
      api_key: os.environ/GEMINI_API_KEY

Start litellm:

litellm --config /path/to/config.yaml

# RUNNING on http://0.0.0.0:4000

Test Request

curl -X POST "http://localhost:4000/v1beta/interactions" \\
  -H "Authorization: Bearer sk-1234" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "gemini/gemini-2.5-flash",
    "input": "Tell me a short joke about programming."
  }'

Streaming:

curl -N -X POST "http://localhost:4000/v1beta/interactions" \\
  -H "Authorization: Bearer sk-1234" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "gemini/gemini-2.5-flash",
    "input": "Write a 3 paragraph story about a robot.",
    "stream": true
  }'

Get Interaction:

curl "http://localhost:4000/v1beta/interactions/{interaction_id}" \\
  -H "Authorization: Bearer sk-1234"

Point the Google GenAI SDK to LiteLLM Proxy:

from google import genai

# Point SDK to LiteLLM Proxy
client = genai.Client(
    api_key="sk-1234",  # Your LiteLLM API key
    http_options={"base_url": "http://localhost:4000"},
)

# Create an interaction
interaction = client.interactions.create(
    model="gemini/gemini-2.5-flash",
    input="Tell me a short joke about programming."
)

print(interaction.outputs[-1].text)

Streaming:

from google import genai

client = genai.Client(
    api_key="sk-1234",  # Your LiteLLM API key
    http_options={"base_url": "http://localhost:4000"},
)

for chunk in client.interactions.create_stream(
    model="gemini/gemini-2.5-flash",
    input="Write a story about space exploration.",
):
    print(chunk)

Request/Response Format

Request Parameters

Response Format

{
  "id": "interaction_abc123",
  "object": "interaction",
  "model": "gemini-2.5-flash",
  "status": "completed",
  "created": "2025-01-15T10:30:00Z",
  "updated": "2025-01-15T10:30:05Z",
  "role": "model",
  "outputs": [
    {
      "type": "text",
      "text": "Why do programmers prefer dark mode? Because light attracts bugs!"
    }
  ],
  "usage": {
    "total_input_tokens": 10,
    "total_output_tokens": 15,
    "total_tokens": 25
  }
}

Calling non-Interactions API endpoints (/interactions to /responses Bridge)

LiteLLM allows you to call non-Interactions API models via a bridge to LiteLLM's /responses endpoint. This is useful for calling OpenAI, Anthropic, and other providers that don't natively support the Interactions API.

Python SDK Usage

# Set API key
os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

# Non-streaming interaction
response = litellm.interactions.create(
    model="gpt-4o",
    input="Tell me a short joke about programming."
)

print(response.outputs[-1].text)

LiteLLM Proxy Usage

Setup Config:

model_list:
- model_name: openai-model
  litellm_params:
    model: gpt-4o
    api_key: os.environ/OPENAI_API_KEY

Start Proxy:

litellm --config /path/to/config.yaml

# RUNNING on http://0.0.0.0:4000

Make Request:

curl http://localhost:4000/v1beta/interactions \\
  -H "Content-Type: application/json" \\
  -H "Authorization: Bearer sk-1234" \\
  -d '{
    "model": "openai-model",
    "input": "Tell me a short joke about programming."
  }'

Supported Providers