Processing 500 lines of code (~5,600 tokens) with Amazon Nova Micro costs $0.000196 for codebase ingestion and $0.000353 for an AI-powered code review and refactoring pass.
Quick answer
A 500 lines of code codebase is estimated at 5,600 tokens for Amazon Nova Micro. Ingestion costs $0.000196; a review and refactoring pass with roughly 20% output costs about $0.000353.
Method & trust
Code is estimated at a tokenizer-specific tokens-per-line ratio, then priced separately for repository context and generated review output. Comments, minified files, tests, and repeated context can materially change the bill.
Feed 500 lines of code into the prompt context for repository search, Q&A, or architecture planning.
Ingest 500 lines of code and generate audit findings, unit test recommendations, and refactor diffs.
Amazon Nova Micro writes 500 lines of code from scratch based on product specifications.
| Model | Provider | Code Ingestion | Cached Ingestion | Code Review Cost | Context Limit |
|---|---|---|---|---|---|
| Amazon Nova Micro (Current) | amazon | $0.000196 | $0.000049 | $0.000353 | 128,000 |
| GPT-5.6 Luna | openai | $0.00102 | $0.000102 | $0.002244 | 1,050,000 |
| GPT-5.4 mini | openai | $0.003825 | $0.000383 | $0.008415 | 256,000 |
| GPT-5.4 nano | openai | $0.00102 | $0.000102 | $0.002295 | 128,000 |
| GPT-4o mini | openai | $0.000765 | $0.000383 | $0.001377 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.0056 | $0.00056 | $0.0112 | 1,000,000 |
On average, code yields approximately 11.2 tokens per line in Amazon Nova Micro (tiktoken_cl100k tokenizer). Indentation, brackets, camelCase variable names, and comments slightly increase token density compared to plain English text. 500 lines of code produces approximately 5,600 tokens.
Sending 500 lines of code as context and generating a thorough code review with recommendations costs approximately $0.000353. Utilizing prompt caching on repeat turns or static repository definitions drops this to $0.000206.
Amazon Nova Micro has a context window of 128,000 tokens. 500 lines of code consumes 4.38% of its total available context.