anthropic · Claude Haiku
Claude Haiku 4.5
Pricing, context window, and capabilities for Claude Haiku 4.5.
| Spec | Claude Haiku 4.5 |
|---|---|
| Provider | anthropic |
| Family | Claude Haiku |
| Status | current |
| Release date | 2025-10-15 |
| Knowledge cutoff | 2025-02 |
| Context window | 200,000 tokens |
| Max output tokens | 64,000 tokens |
| Input price | $1.00/MTok |
| Output price | $5.00/MTok |
| Cached input price | $0.10/MTok |
| Vision | Yes |
| Tool use | Yes |
| Extended thinking | Yes |
| Streaming | — |
Strengths
- The only current Claude model that supports classic extended thinking.
- Uses the older Claude tokenizer, so token counts are ~30% lower than Sonnet 5 for the same text.
- Reliable knowledge cutoff of Feb 2025 is the oldest in the current Claude lineup.
- 200k context window against 1M on every other current Claude model.
- Does not support adaptive thinking.
Compare Claude Haiku 4.5 to other models
Claude Haiku 4.5 vs Claude Fable 5.1Claude Haiku 4.5 vs Claude Sonnet 5Claude Haiku 4.5 vs DeepSeek-V4.1-FlashClaude Haiku 4.5 vs DeepSeek-V4-Pro-0813Claude Haiku 4.5 vs Gemini 3.1 Flash-LiteClaude Haiku 4.5 vs Gemini 3.1 ProClaude Haiku 4.5 vs Gemini 3.8 FlashClaude Haiku 4.5 vs GPT-5.4 miniClaude Haiku 4.5 vs GPT-5.6 LunaClaude Haiku 4.5 vs GPT-5.6 SolClaude Haiku 4.5 vs GPT-5.6 TerraClaude Haiku 4.5 vs GPT-6 AstraClaude Haiku 4.5 vs Grok 4.3Claude Haiku 4.5 vs Grok 4.5Claude Haiku 4.5 vs Kimi K2.6
Not sure which model to use?
Flaibo is a daily AI orientation hub: a 12-week path and a prompt vault, with Free and Professional plans. Build the habit, not just the comparison.
Start your AI path