Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Haiku 4.5 is a workhorse that makes the coding experience in Claude Code feel really fast. While Sonnet 4.5 remains the default, Haiku 4.5 now powers the Explore subagent which can rapidly gather context on your codebase to build apps even faster.

205,593 görüntüleme • 1 yıl önce •via X (Twitter)

40 Yorum

cat profil fotoğrafı
cat1 yıl önce

You can select Haiku 4.5 to be your default model in /model. When selected, you’ll automatically use Sonnet 4.5 in Plan mode and Haiku 4.5 for execution for smarter plans and faster results. To enter Plan mode, hit `Shift + Tab + Tab`

cat profil fotoğrafı
cat1 yıl önce

Haiku 4.5 is a great way to extend your Claude Code usage on the Pro plan. Haiku 4.5 is $1 per million input tokens and $5 per million output tokens, which means it is priced 3x lower than Sonnet 4.5 and slightly higher than Haiku 3.5.

cat profil fotoğrafı
cat1 yıl önce

Let us know how it feels to use Haiku 4.5 in Claude Code. We’re excited to keep making it better.

J Liew profil fotoğrafı
J Liew1 yıl önce

Claude Code v2.0.17 I don't see the option to choose Haiku 4.5 using /model

Alex Finn profil fotoğrafı
Alex Finn1 yıl önce

amazing! needed a lightweight Anthropic model for the agent I'm building. Playing around with it all day

cat profil fotoğrafı
cat1 yıl önce

let us know what you think!

elvis profil fotoğrafı
elvis1 yıl önce

Cool! It does sound like Haiku 4.5 will be great to build subagents. Can't wait to test this out with my subagents.

Eng1neerJack profil fotoğrafı
Eng1neerJack1 yıl önce

@claudeai is making people hit pay barriers more and more - you have to keep paying more and more to get services. This might be good for now - but soon im sure another company will replace it. If claude keeping being tight - it will be replaced.

CJ profil fotoğrafı
CJ1 yıl önce

We don’t need new models. Fix the ones you nerfed instead.

Mukul. 🚀 profil fotoğrafı
Mukul. 🚀1 yıl önce

How is Haiku on writing tasks? If I wish to repurpose CC to be more of a researcher or writer agent, will this be a good segue?

cat profil fotoğrafı
cat1 yıl önce

Yes, I use CC for this :)

Mukul. 🚀 profil fotoğrafı
Mukul. 🚀1 yıl önce

Exciting! Thanks for building a great product :)

Aditya Saxena profil fotoğrafı
Aditya Saxena1 yıl önce

i'm on the max plan but my usage limits don't reset anymore (been seeing this error since 2 days):

thoughtlesslabs profil fotoğrafı
thoughtlesslabs1 yıl önce

welp - there goes my week

Conwic profil fotoğrafı
Conwic1 yıl önce

Does it contain lead?

Vishnu Anand profil fotoğrafı
Vishnu Anand1 yıl önce

But actually it is indeed a good model to try building agents…

Alexander Riccio (@co2trackers) profil fotoğrafı
Alexander Riccio (@co2trackers)1 yıl önce

Quick question: does haiku 4.5 have the same 200k token context window limit?

Jon Chu profil fotoğrafı
Jon Chu1 yıl önce

For bug fixes seems like haiku will be the way to go

Cody Hergenroeder 🍋⚡️ profil fotoğrafı
Cody Hergenroeder 🍋⚡️1 yıl önce

YOOO this is so handy to have in the subagent repertoire for extending claude's capabilities :') gonna use haiku in much the same way you are, to extend claude's Fog of War view in massive knowledgebases!

Agam Chaudhary profil fotoğrafı
Agam Chaudhary1 yıl önce

A strong sign of how AI tooling is maturing from capability to usability. Speed and context awareness are becoming the real differentiators. Do you think this kind of embedded agent design will redefine how developers approach problem solving?

Paul profil fotoğrafı
Paul1 yıl önce

solid!!

Der.dev 🔥🛠️ profil fotoğrafı
Der.dev 🔥🛠️1 yıl önce

🫶🏿🧠

Benita profil fotoğrafı
Benita1 yıl önce

I really didn’t think Speed would be such a game changer for me, that it would always be about using the “best” (smartest) model. I was wrong.

Lane profil fotoğrafı
Lane1 yıl önce

Shame Claude doesn't actually work.. the few times it did work, worked well. Back to GPT.

Conor Dart profil fotoğrafı
Conor Dart1 yıl önce

im trying to understand where Haiku 4.5 fits in claude code? can anyone help me understand better

BB🍓🍓🍓 profil fotoğrafı
BB🍓🍓🍓1 yıl önce

The latest version of Claude Code doesn’t have the Opus Plan mode anymore — is there any way to bring it back?

Casey Whalen profil fotoğrafı
Casey Whalen1 yıl önce

Extremely excited to test out this new model.

Suhrab Khan⚡️ profil fotoğrafı
Suhrab Khan⚡️1 yıl önce

Haiku 4.5’s speed advantage and context-gathering capabilities make it ideal for rapid app development, complementing Sonnet 4.5 for deep code exploration.

Hayden Lingle profil fotoğrafı
Hayden Lingle1 yıl önce

Too many limits. Had to get codex since it’s been so bad.

AICarnal profil fotoğrafı
AICarnal1 yıl önce

I suspect that this model was used in the recent beta testing of Claude OS. I think it's ideal for web searches, and it's quite pleasant to converse with. Speed is very important, part of the future lies with Haiku.

Mehreen Omer profil fotoğrafı
Mehreen Omer1 yıl önce

Simply beautiful

Caden Burleson profil fotoğrafı
Caden Burleson1 yıl önce

Now edit a dropdown menu…

VibeEdge profil fotoğrafı
VibeEdge1 yıl önce

Impressive speed and efficiency with Haiku 4.5! The demo really showcases its potential for rapid prototyping. Excited to see how it performs in real-world projects great work!

🙃 Ben WΞst 🦋 profil fotoğrafı
🙃 Ben WΞst 🦋1 yıl önce

impressive, looking forward to seeing the impact this has on sub agent work.

Rehan profil fotoğrafı
Rehan1 yıl önce

Sounds interesting

Yuanhao profil fotoğrafı
Yuanhao1 yıl önce

My vibe flow: Sonnet 4.5 + ultrathink 🫣

Bilal Bakr profil fotoğrafı
Bilal Bakr1 yıl önce

So its like the Claude 4.5 lite version?

Sri Agung profil fotoğrafı
Sri Agung1 yıl önce

Haiku > Sonnet, fr/fr

Mr. Code NJ profil fotoğrafı
Mr. Code NJ1 yıl önce

It's fast but not as smart. I prefer accuracy over speed.

KLX profil fotoğrafı
KLX1 yıl önce

I just tried to do a pretty simple financial task Sonnet 4.5 does fine and it basically told me I’m a criminal and it can’t help me 💀😂 it seems to either lack a very basic understanding of the world or is WAY too overcautious, or both?

Benzer Videolar

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

Alvaro Cintas

58,450 görüntüleme • 1 ay önce