Prompt Caching

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.ephone.ai/anthropic",
    api_key="API_KEY",
)

# First request
response = client.messages.create(
    model="claude-opus-4-5-20251101",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
)

response_id = response.id

# Second request — include response ID to stay on the same channel
response2 = client.messages.create(
    model="claude-opus-4-5-20251101",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"},
        {"role": "assistant", "content": response.content[0].text},
        {"role": "user", "content": "Continue our conversation..."},
    ],
    extra_headers={"X-Response-Id": response_id}
)

# After the first request, extract the X-Rixapi-Request-Id header from the response

# Include it in the next request
curl https://api.ephone.ai/anthropic/v1/messages \
  -H "x-api-key: API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "X-Request-Id: 202511162255194339355347BE3UyUY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-opus-4-5-20251101", "max_tokens": 1024, "messages": [...]}'