Processing 100,000 lines of code (~980,000 tokens) with Codestral 2501 costs $0.294 for codebase ingestion and $0.4704 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.
Codestral 2501 writes 100,000 lines of code from scratch based on product specifications.
| Model | Provider | Code Ingestion | Cached Ingestion | Code Review Cost | Context Limit |
|---|---|---|---|---|---|
| Codestral 2501 (Current) | mistral | $0.294 | $0.0294 | $0.4704 | 256,000 |
| GPT-5.3 Codex | openai | $1.785 | $0.1785 | $4.641 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.1568 | $0.0157 | $0.2195 | 128,000 |
| Grok Build 0.1 | xai | $1.12 | $0.224 | $1.568 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.224 | $0.0224 | $0.3584 | 128,000 |
| DeepInfra — Qwen 2.5 Coder 32B | deepinfra | $0.0896 | $0.0224 | $0.1434 | 128,000 |
On average, code yields approximately 9.8 tokens per line in Codestral 2501 (mistral_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 980,000 tokens.
Sending 100,000 lines of code as context and generating a thorough code review with recommendations costs approximately $0.4704. Utilizing prompt caching on repeat turns or static repository definitions drops this to $0.2058.
Codestral 2501 has a context window of 256,000 tokens. 100,000 lines of code consumes 382.81% of its total available context.