AI / Claude Models Basics Interview Questions
What is Claude Haiku 4.5 and what are its key characteristics?
Claude Haiku 4.5 (claude-haiku-4-5-20251001, alias claude-haiku-4-5) is Anthropic's fastest and most cost-efficient model in the current generation. It is described as achieving near-frontier performance on coding, computer use, and agent tasks while being optimised for speed and low latency.
| Property | Value |
|---|---|
| API ID | claude-haiku-4-5-20251001 (alias: claude-haiku-4-5) |
| Context window | 200,000 tokens |
| Max output tokens | 64,000 tokens |
| Pricing (input) | $1 per million tokens |
| Pricing (output) | $5 per million tokens |
| Thinking | Extended thinking (opt-in, explicit reasoning blocks) |
| Context awareness | Yes — tracks its token budget throughout a conversation |
| Best for | High-throughput, latency-sensitive tasks; customer service; simple classification |
Extended thinking on Haiku 4.5: unlike the Opus and Sonnet tier which use adaptive thinking, Haiku 4.5 supports the explicit extended thinking mode where reasoning steps appear as visible <thinking> blocks in the API response. This is opt-in via the thinking parameter.
Haiku 4.5 was announced as matching Sonnet 4's performance on coding, computer use, and agent tasks while costing significantly less per token.
What is the context window size for Claude Haiku 4.5?
What type of thinking does Claude Haiku 4.5 support?
More Related questions...
