Processing 100 lines of code (~1,120 tokens) with Gemma 2 9B Instruct costs $0.000224 for codebase ingestion and $0.000269 for an AI-powered code review and refactoring pass.
Feed 100 lines of code into the prompt context for repository search, Q&A, or architecture planning.
Ingest 100 lines of code and generate audit findings, unit test recommendations, and refactor diffs.
Gemma 2 9B Instruct writes 100 lines of code from scratch based on product specifications.
| Model | Provider | Code Ingestion | Cached Ingestion | Code Review Cost | Context Limit |
|---|---|---|---|---|---|
| Gemma 2 9B Instruct (Current) | $0.000224 | $0.000056 | $0.000269 | 8,192 | |
| GPT-5.6 Luna | openai | $0.000204 | $0.000020 | $0.000449 | 1,050,000 |
| GPT-5.4 mini | openai | $0.000765 | $0.000077 | $0.001683 | 256,000 |
| GPT-5.4 nano | openai | $0.000204 | $0.000020 | $0.000459 | 128,000 |
| GPT-4o mini | openai | $0.000153 | $0.000077 | $0.000275 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.00112 | $0.000112 | $0.00224 | 1,000,000 |
On average, code yields approximately 11.2 tokens per line in Gemma 2 9B Instruct (sentencepiece tokenizer). Indentation, brackets, camelCase variable names, and comments slightly increase token density compared to plain English text. 100 lines of code produces approximately 1,120 tokens.
Sending 100 lines of code as context and generating a thorough code review with recommendations costs approximately $0.000269. Utilizing prompt caching on repeat turns or static repository definitions drops this to $0.000101.
Gemma 2 9B Instruct has a context window of 8,192 tokens. 100 lines of code consumes 13.67% of its total available context.