How do I save up to 75% with prompt caching and batch routing?

import anthropic
 
client = anthropic.Anthropic(
    api_key="sk-cog-YOUR-PROXY-KEY",
    base_url="https://api.cognocient.com/v1",
)
 
# Your large, stable system prompt
SYSTEM_PROMPT = """
You are a helpful support agent for Acme Corp.
[... 10,000 tokens of product documentation, FAQs, policies ...]
"""
 
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system=[
        {
            "type": "text",
            "text": SYSTEM_PROMPT,
            "cache_control": {"type": "ephemeral"},  # <-- mark for caching
        }
    ],
    messages=[
        {"role": "user", "content": user_question}  # only this changes per call
    ],
    extra_headers={
        "X-Cost-Feature": "support-chat",
    },
)
 
# Cognocient dashboard shows:
# cache_write_input_tokens: 10,000 (first call only)
# cache_read_input_tokens:  10,000 (all subsequent calls — 90% cheaper)

# OpenAI — prompt caching is automatic, nothing to change
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": LARGE_SYSTEM_PROMPT},  # cached automatically if ≥1024 tokens
        {"role": "user", "content": user_question},
    ],
    extra_headers={"X-Cost-Feature": "support-chat"},
)
 
# Cognocient dashboard shows usage breakdown:
# prompt_tokens:        10,240
# prompt_tokens_cached:  9,800  (at 50% discount)
# completion_tokens:       180

import json
from openai import OpenAI
 
client = OpenAI(
    api_key="sk-cog-YOUR-PROXY-KEY",
    base_url="https://api.cognocient.com/v1",
)
 
# 1. Prepare batch requests as JSONL
documents = load_documents()  # e.g., 1,000 contracts to analyse
 
requests_jsonl = []
for i, doc in enumerate(documents):
    requests_jsonl.append(json.dumps({
        "custom_id": f"doc-{i}",
        "method": "POST",
        "url": "/v1/chat/completions",
        "body": {
            "model": "gpt-4o-mini",
            "messages": [
                {"role": "system", "content": "Extract key clauses from this contract."},
                {"role": "user", "content": doc.text},
            ],
            "max_tokens": 500,
        },
    }))
 
# 2. Upload the batch file
batch_file = client.files.create(
    file=("batch.jsonl", "\n".join(requests_jsonl).encode()),
    purpose="batch",
)
 
# 3. Submit the batch (50% off — up to 24h turnaround)
batch = client.batches.create(
    input_file_id=batch_file.id,
    endpoint="/v1/chat/completions",
    completion_window="24h",
    metadata={"feature": "contract-extractor"},  # for Cognocient attribution
)
 
print(f"Batch submitted: {batch.id}")
# Check later: client.batches.retrieve(batch.id)