# 1. Use Turbo variants (faster, cheaper, similar quality)
# meta-llama/Llama-3.3-70B-Instruct-Turbo vs Llama-3.1-70B-Instruct

# 2. Batch inference (50% cost reduction)
batch_response = client.batch.create(
    input_file_id=file_id,
    model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
    completion_window="24h",
)

# 3. Cache responses for identical prompts
from functools import lru_cache

@lru_cache(maxsize=1000)
def cached_completion(prompt: str, model: str) -> str:
    response = client.chat.completions.create(
        model=model, messages=[{"role": "user", "content": prompt}],
    )
    return response.choices[0].message.content

# 4. Use smallest model that works
# Test with 3B first, upgrade to 70B only if quality insufficient