Processing 1,000 lines of code (~11,200 tokens) with Gemini 2.5 Flash costs $0.00336 for codebase ingestion and $0.00896 for an AI-powered code review and refactoring pass.
Feed 1,000 lines of code into the prompt context for repository search, Q&A, or architecture planning.
Ingest 1,000 lines of code and generate audit findings, unit test recommendations, and refactor diffs.
Gemini 2.5 Flash writes 1,000 lines of code from scratch based on product specifications.
| Model | Provider | Code Ingestion | Cached Ingestion | Code Review Cost | Context Limit |
|---|---|---|---|---|---|
| Gemini 2.5 Flash (Current) | $0.00336 | $0.00084 | $0.00896 | 1,000,000 | |
| GPT-5.6 Luna | openai | $0.00204 | $0.000204 | $0.004488 | 1,050,000 |
| GPT-5.4 mini | openai | $0.00765 | $0.000765 | $0.0168 | 256,000 |
| GPT-5.4 nano | openai | $0.00204 | $0.000204 | $0.00459 | 128,000 |
| GPT-4o mini | openai | $0.00153 | $0.000765 | $0.002754 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.0112 | $0.00112 | $0.0224 | 1,000,000 |
On average, code yields approximately 11.2 tokens per line in Gemini 2.5 Flash (sentencepiece tokenizer). Indentation, brackets, camelCase variable names, and comments slightly increase token density compared to plain English text. 1,000 lines of code produces approximately 11,200 tokens.
Sending 1,000 lines of code as context and generating a thorough code review with recommendations costs approximately $0.00896. Utilizing prompt caching on repeat turns or static repository definitions drops this to $0.00644.
Gemini 2.5 Flash has a context window of 1,000,000 tokens. 1,000 lines of code consumes 1.12% of its total available context.