Rate limits and usage caps

Would you mind sharing that prompt? I'm struggling to even hit 10% of my Claude quota!

jamiejquinn · Oct 23, 2026 · comment in “Kimi K3.1 Pro and K3.1 Pro Highspeed”

Does Anthropic have something similar. I understand "claude -p" has been unreliable to use with subscription quota and often required "extra usage" credits.

albert_e · Oct 22, 2026 · comment in “OpenAI CLI”

This is definitely a real problem lol. I dont use much coding agents my self but sometimes when im in the middle of a session and when the rate limit hits it gets annoying so yea I see why people need this.

varman11 · Oct 1, 2026 · comment in “Etymon – Get rid of all your Claude.md, AGENTS.md, cursor/rules, mcp.json, etc.”

Show HN: Text alerts when Codex resets are announced I built this out of my usage limit frustration in Codex.

samfeldman · Sep 29, 2026 · story in “Show HN: Text alerts when Codex resets are announced”

SKILL.md covers what it gets wrong (API version, rate limits, etc.) and points at the vendor's own API docs for anything else. The annoying part isn't tool calling, it's auth.

byungkyu · Sep 22, 2026 · comment in “MCP was always a bad idea?”

I built VernLLM cuz every LLM gateaway I looked at, meant adding a network hop just to get rate limiting, multi provider fallback, circuit breaking and other features. Needing to take a whole seperate service just to deploy, monitor and trust with my API keys is just annoying since my whole tech stack was just TypeScript and Node.

Buddo · Sep 6, 2026 · story in “Show HN: I stopped using an LLM gateway and put rate-limits/fallback in-process”

The shades of gray of these 2 companies are so close, I can hardly tell them apart. Anthropic kept changing their terms of service (openclaw agent use) while only using X.com to make/counter their own announcements, doesn’t offer Fable with ZDR, use quota and refuse to give you the work due to guardrails triggering, had some crazy unreliable service periods, continually change what’s offered in their base paid plan,…

nickthegreek · Sep 1, 2026 · comment in “ChatGPT Work Tool and Skill Reference”

Instead of a new model that's going to have unreasonably shallow usage limits, I wish they would:

rybosworld · Sep 1, 2026 · comment in “Claude Fable 5.1 and Claude Mythos 5.1”

Compared $20 ChatGPT and AGY plan: my weekly limit on sol/terra used to disappear in one intensive day (or two normal ones). Now they’ve added the 5-hour limit on top of that, which is even more annoying.

dan_voronov · Sep 1, 2026 · comment in “Google Antigravity introduces Boost deep reasoning (/boost)”

Sandbox accounts, live secrets in CI, rate limits, flaky suites because the mock didn't behave like the real thing.

polymatto · Aug 18, 2026 · story in “Show HN: Stunt – a stunt double for the APIs you integrate (95 adapters)”

Claude offers money credits and double usages but take them out and Claude becomes almost unusable where it would take opus about two - three high effort conversations to exhaust my session quota in Pro.

eternaldao · Aug 14, 2026 · comment in “Why does Opus 5 feel worse to work with?”

At least that's how I perceive it. But again, the main problem with Claude is running out of quota in the middle of research or implementing a task.

docheinestages · Aug 14, 2026 · comment in “Why does Opus 5 feel worse to work with?”

On top of that, with usage limits being what they are lately, a lot of people are buying multiple Codex and Claude Code accounts. Switching between them by hand every time you hit a limit is a real pain.

asdsa112 · Aug 3, 2026 · story in “Show HN: AgentCodeGUI – Multi-Account Desktop GUI for Claude Code and Codex”

But I got tired of the terminal as the interface: I tried Termius on my phone but it was quite painful the moment I tried to paste screenshots or record voice notes. The best thing I found was Claude's remote-control feature, but it locks me to one coding agent / LLM provider, and therefore I'm stuck as soon as I hit my usage limit.

sebderhy · Jul 29, 2026 · comment in “ShellTeam – web app to steer coding agents on your VPS”

I've tried Sourcebot (just for the code search, I don't care about "MCP"/"AI") etc, but was wondering if anyone has recommendations. GitHubs code search is great, but it doesn't find everything, and it is also incredibly rate limited (annoying when trying to narrow something down, and you then get rate limited).

thejosh · Jul 24, 2026 · comment in “I regret migrating to Codeberg”

Show HN: Claudexor – quota-aware routing for Claude Code, Codex, and Cursor I am tired of switching between agents when I run out of quota limits.

abstractDL · Jul 21, 2026 · story in “Show HN: Claudexor – quota-aware routing for Claude Code, Codex, and Cursor”

if you happen to regenerate your protos 5 times in an hour you'll get ratelimited it's a very frustrating system. you should spend a modicum of effort figuring out how to generate your things locally yourself instead, be that docker, arcane wasm...

Scaevolus · Jul 14, 2026 · comment in “Protobuf-py: Protobuf for Python, without compromises”

I recently have been testing ChatGPT business at work and the quota seems to disappear almost instantly even using weaker models. Unless they dramatically increase their quotas it’ll be unusable.

shusaku · Jul 6, 2026 · comment in “GPT-5.6 Sol Ultra will be in Codex”

I use Claude Code on a Max plan, and the usage limits, like for all of us (and esp. with dedicated Fable limits now) dictate how I will plan my day/sessions. It was super goddamn annoying clicking the usage wheel (perhaps this frustration is shared with /usage in terminal or CLI but I only use the desktop app), so I built this to poll Anthropic endpoint every 60 seconds and stay in my menu bar so I can always just g…

MikaW · Jul 3, 2026 · story in “Show HN: LimitBar, a macOS menu bar app showing your Claude usage limits”

And I had to use my $100 Codex plan to finish the work GLM started before it ran out of quota. And also to fix it since GLM left a bit of a mess.

cmrdporcupine · Jun 22, 2026 · comment in “GLM 5.2 vs. Opus”

I do slightly prefer 5.5 for complex work but Claude quota usage has gotten infinitely better since the dark days a few months back - has gone from being infuriating to something I pretty much don’t have to worry about with it as a daily driver.

efromvt · Jun 9, 2026 · comment in “Claude Fable 5”

Usually what was shaded in the GUI, worked through console. If that does not work, try to loop terraform or hcloud in the console with a 5 minutes sleep time in between retries (mind hetzner api rate limit).

dominikz · May 24, 2026 · comment in “Hetzner us-east, now you can get only the smallest instance (CPX11)”

Yeah, how many agents can you people even run at once and how much does it cost you? In company we used the monthly token quota and nowadays it's basically unusable with claude opus 4.6 on high reasoning.

Tooster · May 22, 2026 · comment in “Launch HN: Superset (YC P26) – IDE for the agents era”

I've had the $20 Gemini plan to use when my local setup runs into tougher problems and the throttling today has been bonkers. I canceled my subscription and will look into upgrading my local setup.

650REDHAIR · May 19, 2026 · comment in “Gemini 3.5 Flash”

The fact I can continue the same chat indicates it is not a quota. Is this intentional behavior by google? if so it is really user hostile and annoying. if a user is hitting a soft limit then warn an store what they typed. don't send the prompt they spent minutes typing oit to /dev/null with no warning. if it is not intentional behavior it is a bug. the app can store my prompt locally or enque without destroying wha…

morpheos137 · May 14, 2026 · story in “Gemini Android App User Hostile Behavior”

The only plan available is maxed out for the month after a few days of serious work, but the AI “experts” are declaring that nobody needs that much. It’s really frustrating to constantly have to juggle quota and lower models.

vjvjvjvjghv · May 12, 2026 · comment in “Amazon employees are "tokenmaxxing" due to pressure to use AI tools”

Mmm....His position of "stopped using markdown altogether for almost everything" strikes me as overstated and selfpromotional. The 2-4x higher generation cost is non-trivial when you're operating under rate limits, and Git versioning friction is a real problem for your work in big and complex repos.

vdelpuerto · May 9, 2026 · comment in “Using Claude Code: The unreasonable effectiveness of HTML”

> First, we’re doubling Claude Code’s five-hour rate limits for Pro, Max, Team, and seat-based Enterprise plans. Ok I guess, this was a bit of a hassle, but you're not increasing my weekly allowance, you're just not annoying me as often.

stavros · May 6, 2026 · comment in “Higher usage limits for Claude and a compute deal with SpaceX”

I assume that 4.6 will become unavailable at some point, but I hope not any time soon. 4.7 hit usage limits faster, didn't do anything obviously better, and had more annoying behaviors in other aspects.

philipkglass · May 6, 2026 · comment in “Agents for financial services and insurance”

I ran out of the quota every single day past week, often twice a day, this never happened before. It's rather unusable for actual professional usage now.

atraac · May 3, 2026 · comment in “Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge”

But I think hackernews is currently way off base when it comes to what's really happening, which is kinda sad considering it use to be "the place" to see what's currently going on. The AI revolution is here, anyone that's cussing about claude code max for 100/month getting rate limited doesn't understand it's already with 2k/month, everyone who's upset that github is focussing on copilot doesn't understand that this…

ddosmax556 · Apr 30, 2026 · comment in “We need a federation of forges”

If you don't pay for it, you don't get much in the way of quota. Earlier on (okay, until recently), Gemini CLI's quota management didn't work very well.

blueg3 · Apr 29, 2026 · comment in “Alphabet Announces First Quarter 2026 Results”

It's why Claude quality is plummeting and people are leaving in droves because the usage limits are pathetic and the API pricing structure is outrageous. All because they can't scale.

petcat · Apr 25, 2026 · comment in “Google plans to invest up to $40B in Anthropic”

Recently dropped CC (which gave me a sense of awe 2 months ago), but they realized GPUs need CapEx and I want to screw around with pi.dev on a budget. Then on to GH Copilot but couldn't understand their cost structure, ran out of quota half month in, now on Codex.

stasomatic · Apr 24, 2026 · comment in “Google plans to invest up to $40B in Anthropic”

I also cancelled my subscription.The $20 Pro plan has become completely unusable for any real work. What is especially frustrating is that Claude Chat and Claude Code now share the exact same usage limits — it makes zero sense from a product standpoint when the workflows are so different.

stan_kirdey · Apr 24, 2026 · comment in “I cancelled Claude: Token issues, declining quality, and poor support”

But these products are all drop in replacements for each other. I've recently favored Codex more than CC, just because rate limits got mildly annoying.

jjfoooo4 · Apr 24, 2026 · comment in “I cancelled Claude: Token issues, declining quality, and poor support”

I have not tried Claude Pro in quite a while and if people are complaining about usage limits I know it's going to be a bad time for me. I had to move up from Claude Pro when the weekly limits were introduced because it was too annoying to schedule my life around 5hr windows.

fluidcruft · Apr 24, 2026 · comment in “I Cancelled Claude: Token Issues, Declining Quality, and Poor Support”

Part of why you're hitting your limit is that Claude's Pro subscription is completely unusable with the current usage limits.

Someone1234 · Apr 24, 2026 · comment in “Ask HN: How are you using AI code assistants on large messy legacy code bases?”

Ask HN: Open-Source Coding Model and Harness at Claude Sonnet / Opus Level Perf? I am tired of Anthropic's rate limits.

connecteev · Apr 23, 2026 · story in “Ask HN: Open-Source Coding Model and Harness at Claude Sonnet / Opus Level Perf?”

Cowork shipped, Hegseth flexed and a lot of people and entire orgs moved from ChatGPT to Claude in the space of a month. They couldn't handle the demand - they quantized their models, dropped effective usage limits and made all kinds of tweaks in Claude Code to reduce token burn.

jeremyjh · Apr 23, 2026 · comment in “Changes to GitHub Copilot individual plans”

Over the past month, I started a GHCP ~$12 Pro sub, and found I hit my quota about half way through March or so (but I also wasn't being very...frugal). So I signed up for Claude (~$20 Pro) for a month, and I liked it at first, but the 5 hour window was very annoying, and I hit it quite a bit.

ThunderSizzle · Apr 22, 2026 · comment in “Changes to GitHub Copilot individual plans”

Afaik Claude has 5 hour rolling window rate limits while Cursor has a monthly window on the $20 plan. The 5 hour window sounds annoying for hobbyists who only use it time to time when they want to dive into some personal project.

yreg · Apr 22, 2026 · comment in “SpaceX says it has agreement to acquire Cursor for $60B”

The advantage Claude has is that the models are more careful and can refactor code instead of leading to bloat as they go. But the throttling happening now is breaking things and making the entire subscription unusable.

dzink · Apr 21, 2026 · comment in “Claude Code to be removed from Anthropic's Pro plan?”

Show HN: Hydra – Never stop coding when your AI CLI hits a rate limit I built Hydra because I kept losing my flow when Claude Code hit usage limits mid-task.

saadn92 · Apr 21, 2026 · story in “Show HN: Hydra – Never stop coding when your AI CLI hits a rate limit”

I got rate limited within an hour on the $200 while working on a single feature. That was the breaking point, I cancelled my subscription.

esperent · Apr 21, 2026 · comment in “Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving”

i do find usage limits frustrating. should prob fork out more...

scrawl · Apr 16, 2026 · comment in “Claude Opus 4.7”

I have never hit a rate limit, but I have seen it get noticeably stupider. It doesn't make me angry, but comments like these are a bit annoying to read, because you are trying to make people sound delusional while, at the same time, confirming everything they're saying.

Capricorn2481 · Apr 16, 2026 · comment in “Claude Opus 4.7”

GitHub have finally wised up that you could run Copilot on a cron and use almost unlimited tokens. They have since made the product unusable by enforcing extremely strict rate limits, annoying many paid customers.

arbol · Apr 15, 2026 · comment in “GitHub Copilot rate limits Pro Users”

>>Anecdotally, Claude on the $20/month plan can only run 1-3 queries per 4 hours before rate limiting, often stopping in the middle of a query. The free version is pretty much unusable.

kamaal · Apr 15, 2026 · comment in “OpenAI's $852B valuation faces investor scrutiny amid strategy shift, FT reports”

It is pretty obvious to me that Anthropic wasn’t prepared with sufficient infrastructure to handle the wave of OpenAI/DoD refugees. Now everyone is getting throttled excessively and Claude is essentially unusable beyond chatting.

voisin · Apr 12, 2026 · comment in “Pro Max 5x quota exhausted in 1.5 hours despite moderate usage”

When a new model is released these issues don't exist I was paying a ton of money for claude, once I stopped and cancelled my subscription entirely, suddenly sonnet 4.6 is performing like opus and I don't have prompts using 10% of my quota in one message despite being the same complexity.

Rekindle8090 · Apr 12, 2026 · comment in “Pro Max 5x quota exhausted in 1.5 hours despite moderate usage”

When a new model is released these issues don't exist I was paying a ton of money for claude, once I stopped and cancelled my subscription entirely, suddenly sonnet 4.6 is performing like opus and I don't have prompts using 10% of my quota in one message despite being the same complexity.

Rekindle8090 · Apr 12, 2026 · comment in “Pro Max 5x quota exhausted in 1.5 hours despite moderate usage”

For context, with Google AI Pro, I can burn through the Antigravity weekly limit in 1-2 hours if I force it to use Gemini 3.1 Pro. Meanwhile Gemini 3 Flash is basically unlimited but frequently produces buggy code or fail to implement things how I personally would (felt like it doesn't "think" like a software dev)

rzkyif · Apr 12, 2026 · comment in “Pro Max 5x quota exhausted in 1.5 hours despite moderate usage”

I have been doing this kind of thing with Cursor and Codex subscriptions, but they do have annoying rate limits, and Cursor on the Auto model seems to perform poorly if you ask it to do too much work, so I am keen to try out laconic on my local GPU.

jstanley · Apr 12, 2026 · comment in “I run multiple $10K MRR companies on a $20/month tech stack”

This is likely model related since Claude Code has received some bug fixes since. The list of bugs and performance problems appears to keep growing: reduced usage quotas, poor performance with numerous attempts at getting things right, cache invalidation bugs, background requests which have to be disabled explicitly to avoid consuming the quota too fast, Opus appears to be quantized even with high thinking mode, poo…

foofloobar · Apr 7, 2026 · comment in “Issue: Claude Code is unusable for complex engineering tasks with Feb updates”

Use all the loops you want, burn all the tokens you want—just pay what they cost. > is there a way to use the quota that's not 'abuse'?

alwa · Apr 4, 2026 · comment in “Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw”

A single workflow goes from 0 to 100% quota usage almost immediately. For a tool that costs 100+ dollars per month for these higher limits, getting locked out after two prompts is incredibly frustrating.

nikhilgk · Mar 29, 2026 · comment in “Tell HN: Bug in Claude Code CLI is instantly draining usage plan quotas”

Get a few GitHub Copilot accounts at 10 bucks each and use OpenAI models, they have very high usage limits I honestly struggle to even hit with one 10 dollar subscription.

cercatrova · Mar 24, 2026 · comment in “Ask HN: $50 monthly budget, which coding models would you recommend now?”

Its a little frustrating because they give no guidance on what that means - I still get marketing emails or emails about claude code changes - I switched over to OpenAI which at this point is also very decent at coding and their rate limits are much more generous.

CVCO · Mar 14, 2026 · comment in “Ask HN: Anthropic account suspended, anyone reinstated?”

I'm curious to know what exactly you feel is inferior? On the other hand, recently for me, the usage limits in Claude have been inconsistent and frustrating.

begemotz · Mar 10, 2026 · comment in “Tell HN: It's official, I'm done with Claude”