Processing 100,000 lines of code (~1,120,000 tokens) with Claude Sonnet 5 costs $2.24 for codebase ingestion and $4.48 for an AI-powered code review and refactoring pass.
Feed 100,000 lines of code into the prompt context for repository search, Q&A, or architecture planning.
Ingest 100,000 lines of code and generate audit findings, unit test recommendations, and refactor diffs.
Claude Sonnet 5 writes 100,000 lines of code from scratch based on product specifications.
| Model | Provider | Code Ingestion | Cached Ingestion | Code Review Cost | Context Limit |
|---|---|---|---|---|---|
| Claude Sonnet 5 (Current) | anthropic | $2.24 | $0.224 | $4.48 | 1,000,000 |
| GPT-5.6 Terra | openai | $2.04 | $0.204 | $4.488 | 1,050,000 |
| GPT-5.4 Workhorse | openai | $2.55 | $0.255 | $5.61 | 256,000 |
| o3-mini | openai | $1.122 | $0.561 | $2.02 | 200,000 |
| o4-mini | openai | $1.122 | $0.2805 | $2.02 | 256,000 |
| o1-mini | openai | $1.122 | $0.561 | $2.02 | 128,000 |
On average, code yields approximately 11.2 tokens per line in Claude Sonnet 5 (claude_bpe tokenizer). Indentation, brackets, camelCase variable names, and comments slightly increase token density compared to plain English text. 100,000 lines of code produces approximately 1,120,000 tokens.
Sending 100,000 lines of code as context and generating a thorough code review with recommendations costs approximately $4.48. Utilizing prompt caching on repeat turns or static repository definitions drops this to $2.464.
Claude Sonnet 5 has a context window of 1,000,000 tokens. 100,000 lines of code consumes 112.00% of its total available context.