System card: https://assets.anthropic.com/m/99128ddd009bdcb/original/Clau...
Claude Haiku 4.5
anthropic.com
Claude Haiku 4.5
1–10 of 292 posts
Re: Claude Haiku 4.5
#2$1/M input tokens and $5/M output tokens is good compared to Claude Sonnet 4.5 but nowadays thanks to the pace of the industry developing smaller/faster LLMs for agentic coding, you can get comparable models priced for much lower which matters at the scale needed for agentic coding.
Given that Sonnet is still a popular model for coding despite the much higher cost, I expect Haiku will get traction if the quality is as good as this post claims.
Re: Claude Haiku 4.5
#3What is the use case for these tiny models? Is it speed? Is it to move on device somewhere? Or is it to provide some relief in pricing somewhere in the API? It seems like most use is through the Claude subscription and therefore the use case here is basically non-existent.
Re: Claude Haiku 4.5
#4What is the use case for these tiny models? Is it speed? Is it to move on device somewhere? Or is it to provide some relief in pricing somewhere in the API? It seems like most use is through the Claude subscription and therefore the use case here is basically non-existent.
They are great for building more specialized tool calls that the bigger models can call out to in agentic loops.
Re: Claude Haiku 4.5
#5$1/M input tokens and $5/M output tokens is good compared to Claude Sonnet 4.5 but nowadays thanks to the pace of the industry developing smaller/faster LLMs for agentic coding, you can get comparable models priced for much lower which matters at the scale needed for agentic coding. Given that Sonnet is still a popular model for coding despite the much higher cost, I expect Haiku will get traction if the quality is a…
With caching that's 10 cents per million in. Most of the cheap open source models (which this claims to beat, except glm 4.6) have limited and not as effective caching.
This could be massive.
Re: Claude Haiku 4.5
#6What is the use case for these tiny models? Is it speed? Is it to move on device somewhere? Or is it to provide some relief in pricing somewhere in the API? It seems like most use is through the Claude subscription and therefore the use case here is basically non-existent.
If you look at the OpenRouter rankings for LLMs (generally, the models coders use for vibe/agentic coding), you can see that most of them are in the "small" model class as opposed to something like full GPT-5 or Claude Opus, albeit Gemini 2.5 Pro is higher than expected: https://openrouter.ai/rankings
Re: Claude Haiku 4.5
#7System card: https://assets.anthropic.com/m/99128ddd009bdcb/original/Clau... (edit: discussed here https://news.ycombinator.com/item?id=45596168)
This is Anthropic's first small reasoner as far as I know.
Re: Claude Haiku 4.5
#8What is the use case for these tiny models? Is it speed? Is it to move on device somewhere? Or is it to provide some relief in pricing somewhere in the API? It seems like most use is through the Claude subscription and therefore the use case here is basically non-existent.
One big use-case is that claude code with sonnet 4.5 will delegate into the cheaper model (configurable) more specific, contextful tasks, and spin up 1-3 sub-agents to do so. This process saves a ton of available context window for your primary session while also increasing token throughput by fanning-out.
Re: Claude Haiku 4.5
#9$1/M input tokens and $5/M output tokens is good compared to Claude Sonnet 4.5 but nowadays thanks to the pace of the industry developing smaller/faster LLMs for agentic coding, you can get comparable models priced for much lower which matters at the scale needed for agentic coding. Given that Sonnet is still a popular model for coding despite the much higher cost, I expect Haiku will get traction if the quality is a…
With caching that's 10 cents per million in. Most of the cheap open source models (which this claims to beat, except glm 4.6) have limited and not as effective caching. This could be massive.
$1/M is hardly a big improvement over GPT5's $1.250/M (or Gemini Pro's $1.5/M), and given how much worse Haiku is than those at any kind of difficult problem (or problems with a large context size), I can't imagine it being a particularly competitive alternative for coding. Especially for anything math/logic related, I find GPT5 and Gemini Pro to be significantly better even than Opus (which reflects in their models having won Olympiad prizes while Anthropic's have not).
Re: Claude Haiku 4.5
#10What is the use case for these tiny models? Is it speed? Is it to move on device somewhere? Or is it to provide some relief in pricing somewhere in the API? It seems like most use is through the Claude subscription and therefore the use case here is basically non-existent.
For me speed is interesting. I sometimes use Claude from the CLI with `claude -p` for quick stuff I forget like how to run some docker image. Latency and low response speed is what almost makes me go to Google and search for it instead.