Processing 250 lines of code (~2,450 tokens) with Mistral Small 4 costs $0.000368 for codebase ingestion and $0.000662 for an AI-powered code review and refactoring pass.
Feed 250 lines of code into the prompt context for repository search, Q&A, or architecture planning.
Ingest 250 lines of code and generate audit findings, unit test recommendations, and refactor diffs.
Mistral Small 4 writes 250 lines of code from scratch based on product specifications.
| Model | Provider | Code Ingestion | Cached Ingestion | Code Review Cost | Context Limit |
|---|---|---|---|---|---|
| Mistral Small 4 (Current) | mistral | $0.000368 | $0.000037 | $0.000662 | 128,000 |
| GPT-5.6 Luna | openai | $0.00051 | $0.000051 | $0.001122 | 1,050,000 |
| GPT-5.4 mini | openai | $0.001913 | $0.000191 | $0.004208 | 256,000 |
| GPT-5.4 nano | openai | $0.00051 | $0.000051 | $0.001148 | 128,000 |
| GPT-4o mini | openai | $0.000383 | $0.000191 | $0.000689 | 128,000 |
| Claude Haiku 4.5 | anthropic | $0.0028 | $0.00028 | $0.0056 | 1,000,000 |
On average, code yields approximately 9.8 tokens per line in Mistral Small 4 (mistral_bpe tokenizer). Indentation, brackets, camelCase variable names, and comments slightly increase token density compared to plain English text. 250 lines of code produces approximately 2,450 tokens.
Sending 250 lines of code as context and generating a thorough code review with recommendations costs approximately $0.000662. Utilizing prompt caching on repeat turns or static repository definitions drops this to $0.000331.
Mistral Small 4 has a context window of 128,000 tokens. 250 lines of code consumes 1.91% of its total available context.