Glossary › LLM

Token

Subword unit that LLMs process. "ChatGPT is great" ≈ 4 tokens. Models have context windows (4K-128K tokens). Input tokens are cheaper than output tokens. 1 token ≈ 0.75 words.

Where this is taught

• Cost Optimization & Token Budgets — Phase 8: Production Agent Infrastructure
• OIDC and OAuth 2.0 Token Management — Phase 5: Enterprise Integration & Authentication
• Chameleon and Early-Fusion Token-Only Multimodal Models — Phase 2: Audio-Visual Models
• Emu3: Next-Token Prediction for Image and Video Generation — Phase 2: Audio-Visual Models
• Long-Video Understanding at Million-Token Context — Phase 3: Multimodal Generation
• Context Window Management & Token Economics — Phase 5: Modern LLM Engineering

Related terms

Context Window

More in LLM

Hallucination · Temperature · Context Window · Top-p (Nucleus Sampling) · In-Context Learning · System Prompt · Function Calling

Learn this by building

DeVenture Academy teaches AI engineering through projects, with hands-on labs you run on your own machine using real tools.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card. Or see Pro pricing.

All courses · Pricing · About · FAQ · Glossary