Claude Haiku 4.5
Claude Haiku 4.5
Ten times the price of Haiku 5.5 for weaker answers. Time to move.
Updated
The read
Haiku 4.5 was Anthropic's cheap, quick model for classification, extraction and routing, and it still follows instructions closely without padding. Haiku 5.5 has since arrived at a tenth of the price for prompts under 100,000 tokens, with a far larger context window and much better scores. Anthropic has not announced a retirement date, but it lists 4.5 as a legacy model, and nothing new should be built on it.
Where it shines
- Answers fast enough to sit in a user-facing request path
- Instruction following is well ahead of its size class
- A long production track record
Worth knowing first
- Haiku 5.5 costs a tenth as much for most prompts and is much stronger
- A 200,000-token context, a fifth of its successor's
Index score
71.2
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
- 68 of 73
- Builds
- LLMs
- Category
- Small and fast
- Output
- Text and code over an API
- Pricing
- Paid only
- Best for
- Existing routing and extraction jobs, until they move to Haiku 5.5
Scores are our own editorial judgement, weighted craft 55, speed 10, control 15 and value 20.
Also worth a look
Full index- 11Claude Haiku 5.5Claude Haiku 5.5ProvisionalA small model priced like a rounding error that scores where mid-tier models did last quarter.Small and fastPaid only87.9
- 22GPT-6 LunaGPT-6 LunaProvisionalThe cheap end of GPT-6, and the model free ChatGPT users now talk to.Small and fastPaid only84.9
- 30GPT-5.6 LunaGPT-5.6 LunaProvisionalStill cheap and still capable, but GPT-6 Luna costs half as much.Small and fastPaid only83.0
