Claude Haiku 4.5
Claude Haiku 4.5
Anthropic's cheap, quick one, for the work that does not need a genius.
Updated
The read
Haiku is the model you put behind classification, extraction, routing and first-draft summarising, where latency is the product and the task has a right answer that is not hard to find. It keeps the family's habits: it follows instructions closely and does not pad. It is a generation behind the rest of the line-up, and on anything genuinely difficult that shows immediately.
Where it shines
- Answers fast enough to sit in a user-facing request path
- Instruction following is well ahead of its size class
- Cheap enough to run over an entire dataset
Worth knowing first
- A generation older than the rest of the line-up
- Falls over on multi-step reasoning that the larger models handle
Index score
78.9
Provisional. This score is read from the product's public capability, not from the one-prompt rebuild the fully reviewed entries went through, so treat it as a placing rather than a verdict.
- Rank
- 28 of 53
- Builds
- LLMs
- Category
- Small and fast
- Output
- Text and code over an API
- Pricing
- Paid only
- Best for
- High-volume classification, extraction and routing
Scores are our own editorial judgement, weighted craft 55, speed 10, control 15 and value 20.
Also worth a look
Full index- 13GPT-5.6 LunaGPT-5.6 LunaProvisionalFrontier-family manners at a price that lets you stop counting tokens.Small and fastPaid only83.3
- 31Mistral Small 4Mistral Small 4ProvisionalThe best small open model to build a product on, and the licence has no catch.Small and fastFree tier78.1
- 38Grok 4.20Grok 4.20ProvisionalxAI's fast tier: quick, cheap, and priced by how much context you actually use.Small and fastPaid only76.9
