What Is Context Length / Context Window?
Context length (also context window) describes how much text a model can process in a single request, measured in tokens.
Orders of Magnitude
Section titled “Orders of Magnitude”| Range | Example | Typical Use Case |
|---|---|---|
| 8K to 32K | ~6,000 to 24,000 words | Short chat requests, classification |
| 128K to 256K | ~96,000 to 192,000 words | RAG with multiple documents, long code files |
| 1M+ | ~750,000+ words | Entire code repositories, books |
Why It Matters
Section titled “Why It Matters”A larger context means more input tokens, and therefore higher cost and longer latency. Context length is not “more is always better”, it’s a deliberate cost/latency trade-off.
Recommendation
Section titled “Recommendation”Clarify the actual requirement first. Most use cases don’t need a 1M token context. Prefer targeted RAG over blindly choosing the maximum context window.