ai-cost-auditlisted

# AI Cost Audit ## The Law ``` EVERY LLM FEATURE HAS A COST TRAJECTORY. DISCOVER IT BEFORE 10× SCALE DISCOVERS YOU. "It's cheap enough now" is a claim about current volume, not future volume. "The API has reasonable pricing" is not a projection. Token counts + call volume + cost at 10× scale IS a cost audit. ``` ## When to Use Trigger: - Before launching any LLM feature (pre-launch projection) - When monthly API bill increased > 20% with no obvious cause - Before scaling a feature to a new user segment - Before committing to a model or provider for a high-volume use case ## When NOT to Use - Internal one-off scripts or developer tools with < 50 calls/day — cost is negligible; write the call, move on - Features still in prototype where the call structure will change significantly before launch — audit after the design stabilises - When total monthly API cost is guaranteed < $50 regardless of 10× scale — skip the audit, check the bill quarterly ## The Process ### Step 1 — Count Tokens Precisely Do not estimate. Count: ```python import tiktoken enc = tiktoken.get_encoding("cl100k_base") # cl100k for GPT/Claude def count_tokens(text: str) -> int: return len(enc.encode(text)) # Measure each segment separately print("System prompt:", count_tokens(system_prompt)) print("Avg context:", count_tokens(avg_context_sample)) print("Avg user message:", count_tokens(avg_user_message_sample)) print("Avg output:", count_tokens(avg_output_sample)) ``` Get real samples from lo