ClaudeDetails
Current model

Claude Haiku 4.5

The fastest model with near-frontier intelligence

claude-haiku-4-5-20251001

Context window200,000 tokens
Input price$1 / M tokens
Output price$5 / M tokens

Claude Haiku 4.5 is Anthropic's fastest current model, described as offering near-frontier intelligence, making it well suited to latency-sensitive, high-volume applications, and priced at $1 per million input tokens and $5 per million output tokens. It supports an extended thinking mode for step-by-step reasoning on harder problems, though it lacks the adaptive thinking found in some other current Claude models. Its 200,000-token context window is smaller than that of other current Claude models, which offer up to 1 million tokens.

Strengths

Fastest response times among current Claude models — well suited to latency-sensitive, high-volume use.

Supports extended thinking mode for step-by-step reasoning on harder problems.

Limitations

  • Smaller context window (200k tokens) than other current Claude models (up to 1M).
  • No adaptive thinking, unlike some other current Claude models.

Best use cases

  • The fastest model with near-frontier intelligence