Claude Haiku

“It was already cheaper and more powerful than Haiku 5.5 which was released like a full month after it”

“Being able to directly distill their huge frontier models into Luna/Haiku-level models puts them a step ahead still.”

“Luna 6 and now Haiku 5.5 are both very competitive if not better on all axes that we care about”

“Hauku scores higher on AA Intelligence index, and is also cheaper per Intelligence index task.”

“just seeing the difference between Haiku 4.5 (a year ago) and Haiku 5.5 (today - and 1/10th the cost) was worth it alone”

“It fell short answering some of the questions that required some deeper statistical analysis”

“Finally! I understand Haiku is the less intelligent model, but the gap between Sonnet and Opus has been far too wide”

“They generate svg. You can paste in pngs and they'll convert them to svg with varying degrees of success.”

“You can get 99% of jobs and work done with Haiku/Luna in a collaberating working enviroment.”

“Haiku is a bit more expensive than Luna on < 100k token, but I just don't have any agentic work below 100k”

“for many agentic workflows significant part of the dispatched tasks might be under 100k budget”

“Considering the price, no model comes close to being as good as this. However, it did take an extremely long time.”

“100k tokens is an absurdly low cutoff and it is only applicable to Haiku and not Sonnet or Opus”

“Sometimes you prefer a cheap, fast model, just like how sometimes you prefer a shorter poem.”

“Opus directs and starts haiku/sonnet subagents. Much more efficient than opus reading it all.”

“Why are we assuming that shopping agents are going to be using the model that is easiest to fall for prompt injections?”

“It continues to be absurdly capable for converting natural language to structured JSON based on a set of fairly complex business rules.”

“To ask for web search, simple commands and research, or passing logs to analyze it's more than enough”

“A subagent with a cheap model like haiku or similar is the way to go instead of dumping tool output directly into the main agent context”

“I know that figure is too low but believed it anyway. I've just asked for better figures and it's completely unable to answer accurately.”

“Last time a model exceeded the expectations I had based on the release notes to such an extent was Haiku 4.5”

“using something like Haiku to provide a comma separated list of advanced topics and jargon”

“I don't see a reason to use Sonnet, Haiku, or the smaller GPT models, because their API rates are much higher”

“I compare it to the Haiku models, where you have to go in and be surgical about your changes”

“Models like Haiku are great if you just want to apply JSON structure to some free text.”

“I don't find Haiku useful for actual coding tasks. Good to, ehm, generate commit messages and summaries.”

“they're blatantly confidently wrong often enough that the wasted time is a significant net negative for me”

“I used it on an agentic reasoning task recently (reading a chunk of information and drawing a written conclusion, not writing code) and it did just fine.”

“I think Haiku is fine (e.g.) for any task that you could almost, but not quite, complete with (regex?) find and replace.”

“Then Haiku doesn't work (unless your "complex feature" is just an api endpoint and some UI that consumes it).”

“a fast cheap model with large context (Gemini Flash, Claude Haiku) is more cost-effective than a frontier model”

“there has been no reason to use Haiku or GPT mini/nano/etc over open weights models for a long time now”

“Haiku is cheaper, faster, and better than anything that will run on your local machine.”

“Haiku is fastest and also quite good at this! Because the edits are quite accurate in terms of its this element with this value”

“Haiku 4.5 detected some footers that were on every page and moved them to be the footer at the end of the entire document”

“Even small, cheap models like Gemini Flash or Claude Haiku do an excellent job extracting pure content.”

“Whereas with Sonnet/Haiku, I'm much more guaranteed to have 100% AI assistance throughout my coding session.”

“Haiku sits at this weird middle point where, if you have a well defined task, you can use a smaller/faster/cheaper model”

“Claude-haiku-4.5 was not far behind and was much faster due to the absence of thinking tokens, but much more expensive.”

“Mostly used Claude Haiku 4.5 like 75% of the time, where it failed, switched to the sonnet 4.5”