/responses/compact

Compress conversation history using OpenAI's /responses/compact endpoint.

Usage

LiteLLM Python SDK

response = litellm.compact_responses(
    model="openai/gpt-4o",
    input=[{"role": "user", "content": "Hello, how are you?"}],
    instructions="Be helpful",
    previous_response_id="resp_abc123"  # optional
)

print(response.id)
print(response.object)  # "response.compaction"
print(response.output)

LiteLLM Proxy

curl http://localhost:4000/v1/responses/compact \\
  -H "Content-Type: application/json" \\
  -H "Authorization: Bearer sk-1234" \\
  -d '{
    "model": "openai/gpt-4o",
    "input": [{"role": "user", "content": "Hello"}],
    "instructions": "Be helpful"
  }'

response = httpx.post(
    "http://localhost:4000/v1/responses/compact",
    headers={"Authorization": "Bearer sk-1234"},
    json={
        "model": "openai/gpt-4o",
        "input": [{"role": "user", "content": "Hello"}],
        "instructions": "Be helpful"
    }
)

print(response.json())

Request Parameters

Response Format

{
  "id": "resp_abc123",
  "object": "response.compaction",
  "created_at": 1734366691,
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [...]
    },
    {
      "type": "compaction",
      "encrypted_content": "..."
    }
  ],
  "usage": {
    "input_tokens": 100,
    "output_tokens": 50,
    "total_tokens": 150
  }
}