Prev Next

AI / Claude Models Basics Interview Questions

What is a context window and what are the context window sizes for current Claude models?

A context window is the total number of tokens (words, punctuation, code, etc.) that a model can process in a single request — encompassing the system prompt, all conversation history, tool definitions, and the model's own output. If you exceed the context window, older content must be removed or the request will fail.

Context windows by model
ModelContext windowMax output tokens
Claude Fable 51 million tokens128,000 tokens
Claude Opus 4.81 million tokens128,000 tokens
Claude Sonnet 51 million tokens128,000 tokens
Claude Haiku 4.5200,000 tokens64,000 tokens

Key facts:

  • The 1M token context window is the default for Fable 5, Opus 4.8, and Sonnet 5 — no beta header is needed and it is billed at standard pricing
  • Claude Haiku 4.5 has a smaller 200k token window and 64k max output
  • On the Message Batches API, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, and Sonnet 4.6 support up to 300k output tokens using the output-300k-2026-03-24 beta header
  • A single request can include up to 600 images/PDF pages (100 for 200k models)
What is the context window size for Claude Opus 4.8?
What is the maximum output token limit for Claude Haiku 4.5?

Invest now in Acorns!!! 🚀 Join Acorns and get your $5 bonus!

Invest now in Acorns!!! 🚀
Join Acorns and get your $5 bonus!

Earn passively and while sleeping

Acorns is a micro-investing app that automatically invests your "spare change" from daily purchases into diversified, expert-built portfolios of ETFs. It is designed for beginners, allowing you to start investing with as little as $5. The service automates saving and investing. Disclosure: I may receive a referral bonus.

Invest now!!! Get Free equity stock (US, UK only)!

Use Robinhood app to invest in stocks. It is safe and secure. Use the Referral link to claim your free stock when you sign up!.

The Robinhood app makes it easy to trade stocks, crypto and more.


Webull! Receive free stock by signing up using the link: Webull signup.

More Related questions...

What is Claude and who makes it? What are the current Claude model families and what is each one optimised for? What are the API model IDs for the current Claude models? What is a context window and what are the context window sizes for current Claude models? What are the pricing tiers for current Claude models and how is pricing calculated? What input and output modalities do current Claude models support? What is extended thinking and how does it differ from adaptive thinking in Claude? What platforms and cloud providers is Claude available on? What is the knowledge cutoff for current Claude models? What is the Claude model lifecycle — what do 'Active', 'Legacy', and 'Deprecated' mean? What is Claude Fable 5 and what makes it different from Claude Opus 4.8? What is Claude Mythos 5 and how does it differ from Claude Fable 5? What is Claude Haiku 4.5 and what are its key characteristics? What is prompt caching and how does it reduce costs when using Claude? What is the Messages Batches API and when should you use it? What is tool use (function calling) in Claude and which models support it? What is computer use in Claude and which models support it? What are the different claude.ai plans and what does each include? What is the effort parameter in Claude and which models support it? What is streaming in Claude API responses and how do you use it? What is the system prompt in Claude and how does it affect model behaviour? What is zero data retention (ZDR) and which Claude models support it? What is Claude's approach to safety and what are Constitutional AI principles? What is the difference between an operator and a user in Claude's design? What is Claude's context window and how are tokens counted? What are Claude's rate limits and how are they structured? What is Claude's approach to harmful content — what will and won't it do? What is Claude's max_tokens parameter and how does it relate to the context window? What is the temperature parameter in Claude and how does it affect responses? What are Claude's multimodal capabilities — how does it process images and documents? What are the claude.ai plans and what models does each tier include access to? What is multi-turn conversation handling in Claude and how do you implement it? What are the different stop_reason values in Claude API responses? What is Claude's approach to honesty and what does it mean for Claude to be non-deceptive? What is Claude Code and how does it differ from using Claude directly via the API? What are the Anthropic SDKs and what languages are officially supported? What is Anthropic's policy on model deprecation and how should developers prepare? What are the key differences between Claude 4 and earlier Claude 3 generation models?
Show more question and Answers...

RenovateBot Interview Questions

Comments & Discussions