Claude Haiku 4.5 vs Claude Haiku Latest
Claude Haiku 4.5 (Anthropic) and Claude Haiku Latest (Anthropic) are listed at different prices. Claude Haiku Latest costs less: $0.10 per 1M input tokens and $0.50 per 1M output tokens, against $1.00 and $5.00 for Claude Haiku 4.5. Claude Haiku Latest has the larger context window, 1,000,000 tokens against 200,000 for Claude Haiku 4.5. Claude Haiku Latest charges $0.50 and $2.50 per 1M once a prompt passes 100,000 tokens; Claude Haiku 4.5 keeps one price across its window. Both accept text, images and files and produce text.
Anthropic: Claude Haiku 4.5 and Anthropic: Claude Haiku Latest both accept text, images, and files, produce text, and support tools, structured outputs, response formats, and reasoning. Claude Haiku Latest has a 1,000,000-token context and 128,000-token maximum output, compared with 200,000 and 64,000 tokens for Claude Haiku 4.5.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Claude Haiku 4.5 | Claude Haiku Latest |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Added to catalog | 15 Oct 2025 | 27 Apr 2026 |
| Input, per 1M tokens | $1.00 | $0.10 |
| Output, per 1M tokens | $5.00 | $0.50 |
| Input above 100K tokensPer 1M; long prompts | $1.00 | $0.50 |
| Output above 100K tokens | $5.00 | $2.50 |
| Cached input read, per 1M | $0.10 | $0.01 |
| Context windowTokens | 200,000 | 1,000,000 |
| Max outputTokens | 64,000 | 128,000 |
| Accepts | file, image, text | file, image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Claude Haiku 4.5 | Claude Haiku Latest |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0020 | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.029 | $0.0029 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.040 | $0.0040 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.158 | $0.079 |
Which to choose
Choose Claude Haiku 4.5 if
No row of the table favours Claude Haiku 4.5. The difference, if there is one, is in the answers it writes: try it on your own task.
Claude Haiku 4.5 detailsChoose Claude Haiku Latest if
- Input tokens cost less: $0.10 against $1.00 per 1M
- Output tokens cost less: $0.50 against $5.00 per 1M
- Your prompts often run past 100K tokens: $0.50 against $1.00 per 1M input tokens there
- Cached input costs less: $0.01 against $0.10 per 1M
- You need the larger context window: 1,000,000 tokens against 200,000
- You need longer answers in one response: 128,000 tokens against 64,000
- You want to set how much it reasons before it answers
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.