minimaxir Pricing is...a bit weird. Input
$0.10 / MTok for prompts up to 100,000 tokens
$0.50 / MTok for prompts over 100,000 tokens Output
$0.50 / MTok for prompts up to 100,000 tokens
$2.50 / MTok for prompts over 100,000 tokens 100k tokens is an absurdly low cutoff and it is only
applicable to Haiku and not Sonnet or Opus. It's a low
enough cutoff that it will be quickly exceeded if you are
doing anything with Agents; for typical generation or
Jev-like classifiers, it's a good value and as noted in
this article, that is apparently the vast majority of
Haiku use.In both cases, still much cheaper than Haiku
4.5's $1 input / $5 output and these prices better compete
with GPT-6 Luna. ($0.10 input / $0.50 output, but with no
token threshold [EDIT: the threshold for Luna is
apparently 272k])
|
> dannyw Haiku 5.5 is noticeably smarter than GPT-6 Luna, so I
can see their pricing strategy here.For a while
Anthropic has lacked a cost effective "cheap" LLM for
summarisation, compacting, RAG helpers, etc.These
'ephemeral' workloads are often under 100k tokens, or
can be structured to be under 100k.In some coding
benchmarks, Haiku 5.5 beats Sonnet 5! (Especially
implementation; do a well defined Jira ticket; etc),
it's really impressive how much intelligence per
dollar has grown in just a few short months.
|
> > RussianCow I said this in another comment, but Artificial
Analysis has the cost per task of Haiku on max
roughly equal to that of Sol on medium, and the
latter is significantly more intelligent. (And I'd
wager that Sol probably finishes tasks more
quickly, even with Haiku inference being faster.)
So Haiku really only makes sense on lower
reasoning levels, and only if you care about
intelligence and speed more than you do about cost
effectiveness (where Luna currently dominates).
And that's without even bringing Chinese models
into the mix.
|
> > WinstonSmith84 noticeably smarter remains to be seen in practice.
For now, Haiku is a bit more expensive than Luna
on < 100k token, but I just don't have any agentic
work below 100k, so this is going to be 5x more
expensive than shown on these charts. It's hardly
competitive ...
|
> > > goosejuice No? Don't use these lower end models to work
on small well defined tasks with a frontier
model orchestrating? This approach works very
well for me and don't have any issue staying
under 100k. I have no idea if it's cheaper but
it does seem to be much faster for tasks like
QA.
|
> > flockonus > it's really impressive how much intelligence per
dollar has grown in just a few short months.Open
weights models giving a distant salute from afar
|
> > > pimeys Yes, it was weird to see MiMo and DeepSeek
missing in the article's comparison...
|
> > > > stavros Is Mimo good? I've never tried it, but
I've seen it mentioned three times in this
subthread alone. DSv4.1 is my daily
driver.
|
> > > > > sausagefeet I have been settling on using Mimo 2.6
flash for discovery/research and glm
5.3 flash for implementation. So far
I've been pretty happy with the
results, but mimo can be quite slow.
If speed is an issue, I just switch to
glm 5.3 flash.
|
> > > > > vardalab As context grows, it gets slower and
dramatically slower. Otherwise it's
pretty good.
|
> > > > > pimeys I haven't really tried it that much. I
use GLM 5.3 a lot, especially with
Coralbricks where the cache reads are
free so I can let it think a lot
without breaking the bank in the
following turns. It's really good for
bughunt, planning, and security
work.Maybe I should try the flash...
|
> > > > RussianCow It's not that weird. Most companies
considering paying Anthropic are probably
not considering Chinese models as
alternatives. Many don't even realize they
exist.
|
> > > > > doodlesdev The thing is: availability of
near-SOTA cheap Chinese models is
forcing OAI and Anthropic to bring
prices down and offer more efficient
models, instead of simply focusing on
super expensive SOTA LLMs.
|
> > > > > > RussianCow Is it? I would guess that it's
much more about the race to get
customers as they both near IPO
than anything to do with the
Chinese models.
|
> > > > > > verdverm we are actively preparing to move
our devs from closed to open
models, take it as a piece of
anecdatathe trend in industry is
clear by now though
|
> > > > > > pimeys Yes. We did the same a few weeks
ago. Everybody I talk with in the
EU startup ecosystem is either
doing the same or considering
doing it.
|
> > > > > > verdverm one only has to look at the
providers like OpenRouter and
OpenCode to see the massive swing
since this summer ... or the fear
mongering by Big Ai about open
weights sinceNot surprised by EU
heading that way with how we here
in 'murica are treating the rest
of the worldat this point, there
is no meaningful difference in
day-to-day work
|
> > > > > > RussianCow > one only has to look at the
providers like OpenRouter and
OpenCode to see the massive swing
since this summerDoesn't this have
more to do with LLMs getting more
usage overall? I don't see how
that's a sign that people are
leaving OpenAI/Anthropic.
|
> > > > > epolanski "companies" is a meaningless metric.If
you want to make it about 99% of real
world companies, they are all on
Gemini or Copilot anyway, nobody is
going through legal and procurement to
get models from dubious silicon valley
startups when you have relations with
Microsoft or Google or Amazon from
ages because some benchmark is showing
some minor digit benefit when vibe
coding GTA 6.
|
> > > > > > RussianCow I said "most companies considering
paying Anthropic", which is not
the same as "most companies". I
also don't agree that "nobody" is
doing this; I have lots of
anecdata suggesting otherwise.
Maybe the majority of companies
are using the easy option of
Copilot or Gemini like you said,
but it's nowhere near 99%.
|
> > > > > > lifeisloving Yes it is. Literally every company
Ive spoken too about this only has
MS teams co-pilot lol. Like all of
them are using the most basic form
of AI.They dont even know about
Anthropic and think its just "AI".
By the way this includes one of
the largest power systems design
firms in the world, who helps
build many datacenters... Uses
only MS copilot.
|
> > > > > > blackqueeriroh Do you understand how many
companies there are? Your anecdata
is wholly useless
|
> > > > > > vardalab Well, I can add two more points to
your anecdata.
I personally know of two companies
where only exposure for peasants
is Copilot.
|
> > > > > > drob518 Yep, this doesn't surprise me.
|
> > > > > > lifeisloving Umm, just go look up the whole of
software revenues globally and
compare that to OpenAI. Its very
small. Nobody is paying for SOTA
models outside software
engineering and ancillaries,
except for some outliers fields
like consulting. Then there's
techies in every field who use it,
but not companies
themselves.Companies as a whole,
do not care about this technology,
except tech companies and its
adoption cant even be compared to
CRMs. A company might buy a SaaS
product with AI but most of them
are not purchasing Anthropic
subscriptions lol.
|
> > > > > > tranceylc Vibe coding gta 6 haha
|
> > JacobAsmuth The benchmarks are very long form logic,
knowledge, and coding tasks though. I'm very
interested in Haiku 5.5's performance on
ObviousBench where Luna 6 is currently SotA.
|
> Tiberium There's also a tokenizer efficiency difference: modern
Claude's 100K tokens are about ~60-65K modern GPT
tokens, so in reality the Luna cutoff is much further
away than the Haiku one.You can test with Anthropic's
count_tokens endpoint.
|
> > AtNightWeCode > ...this tokenizer, the same input text produces
approximately 30% more tokens on Claude Haiku 5.5
than on Claude Haiku 4.5.So, it is might be even
worse.
|
> > > Tiberium No, it's just Haiku 4.5 is so old that it
predates the new Claude tokenizer change in
Claude 4.7+
|
> Eridrus It's actually existing flat per-token pricing that is
weird.Neither encode nor decode are linear in compute,
so providers need to price for average expected
length.This is just getting closer to the true cost of
generating tokens.
|
> > foota My theory here is that providers cover the
non-constant costs of output tokens as context
length caries using the cache input fees.
|
> > hgoel Flat per-token pricing is likely just logistically
easier, particularly if these closed models are
also picking up the kv cache efficiency
improvements seen in recent open weight models.
|
> > > vardalab You would think with all this AI available,
they could figure out the pricing to be as
granular as necessary.
|
> > > > anthonypasq96 people dont like when the price of
something is a giant formula or ???
|
> > sebzim4500 Flat pricing is weird too but jumping up 5x at one
cutoff is surprising in the other direction IMO
|
> > > stingraycharles I think this was originally started by Google
who first offered these large context windows
and others just followed suit.
|
> > willsmith72 they don't need to, companies smooth out costs all
the time. cost of goods sold isn't a great way to
price software products
|
> > > stingraycharles Yeah, also, the real cost here is memory, not
compute. Which is why KV cache quantization is
a thing.
|
> HarHarVeryFunny Notable that one suggested use case for Haiku is
"classification requests", i.e. Jev competitor, and
the pricing matches GPT-6 Luna which is behind
OpenAI's "Decisions API" Jev competitor.For this
application 100K token input is plenty.Of course
Anthropic and OpenAI, both at $0.10/M, are still 2.5x
the cost of Jev's $0.04/M.
|
> > martianvoid I think the 2.5 times cost but actually pays off
in terms of intelligence compared to jev and the
general capability of using it beyond
classification
|
> > > HarHarVeryFunny The classification performance remains to be
seen, but presumably we'll soon start to see
classification benchmarks.For other tasks like
summaries (another suggested usage) it's good
to see Haiku and Luna now competing against
each other on cost.I'd love to know how the
business automation market breaks down by
volume of call type though - hard to imagine
that decision making (e.g. branching, triage)
isn't a very large part of it, greater than
these other suggested Haiku use cases.
|
> tr4656 Luna does as well, but just at a higher limit.From
OpenAI's website: Prompts with more than 272K input
tokens are priced at 2x input and cache rates and 1.5x
output for the full request.
|
> > minimaxir Huh, that disclaimer is on the model page
(https://developers.openai.com/api/docs/models/gpt
-6-luna) but not the pricing page. Annoying.Fixed.
|
> > tripleee So even at the 1.5x/2x rate luna is still half the
price of this. Weird pricing strategy from
Anthropic. I'm sticking with Luna if I don't need
a super smart model
|
> > > usef- You're judging purely by token cost I assume,
not cost per completed task?The benchmark in
the article showed it as lower per completed
task than luna, but I guess we'll find out how
representative that is. Anthropic has
generally been fairly honest in their
benchmarking though.
|
> > > > RussianCow The cost per task from Artificial Analysis
is roughly 3x higher at every reasoning
effort level for Haiku than Luna. Sol 6.1
on medium has the same cost per task as
Haiku with significantly higher
intelligence. According to those numbers
(which you should take with a grain of
salt), from a pure cost vs intelligence
standpoint, you're better off using Luna
for economics and Sol for
intelligence.With that said, the real
reason to use Haiku is that it's faster
than all of these models. OpenRouter is
showing an average so far of 93
tokens/sec, and AA got at least 137 in
each of their benchmarks. So it might be
valuable for speed at lower thinking
levels. (At higher thinking levels, it's
likely going to take longer to produce
results than Sol on
low/medium.)https://artificialanalysis.ai/
models/releases/comparisons/cl...
|
> > > > tripleee yes, that's true. I should be looking at
the $/completed task
|
> alexchamberlain Isn't it less than a year since Claude models went
from 100k token limit to 1M limit? Don't get me wrong
- my main agent normally gets to 25% or so before I
clear it these days, but as a subagent, doing research
or summarisation, I don't think 100k is "absurdly
low".
|
> enraged_camel >> 100k tokens is an absurdly low cutoff and it is
only applicable to Haiku and not Sonnet or Opus. It's
a low enough cutoff that it will be quickly exceeded
if you are doing anything with AgentsYour vibes don't
appear to be supported by facts. From the
announcement:>> Claude Haiku 5.5 is priced 90% lower
than Claude Haiku 4.5 for requests up to 100,000
tokens, and 50% lower for requests over 100,000
tokens. On Haiku 4.5, 90% of requests fell into the
former category.
|
> > Philpax People weren't using Haiku 4.5 for agents before.
5.5 is good enough that it might be.
|
> > StilesCrisis Haiku 4.5 users were using it for Kleenex requests
because that was the best it could do.
|
> > > enraged_camel Not really. We use Haiku 4.5 to turn users'
natural language queries and requests into
fairly complex structured specs for interior
design and construction. It has near perfect
accuracy.
|
> > > > dotancohen How many examples are in your prompt? How
large is that prompt? Or do you have some
other way of tuning the output?I'm asking
to learn for a similar project, not to
discount anything you're saying.
|
> jeremyjh If you can't get any coding done with 100K context
that is either a broken model, a broken harness or a
skill issue. I would mostly use Haiku in task or
explorer subagents. I'm not saying I stay under that
on every task, but I do have quite a few sessions that
cap out well below that, so that price difference
would be very meaningful.I use Luna for this day in
and out and its excellent - if Haiku is that much
better I will be changing things up.
|
> > serf >If you can't get any coding done with 100K
context that is either a broken model, a broken
harness or a skill issue."less context is better
and if you can't get stuff done with less yur bad"
is the worst argument ever.it might be pure luxury
to your eyes, but it's great to not require the
use of a special custom harness that transcribes
everything into emoji and compresses everything
into barcode images.it's great to have a million
token context to throw a large project into. If I
need 100k just about any current gen consumer GPU
in the world has very good models that I can self
host for 100k context, limiting myself to 100k on
someone elses machine seems to be missing a lot of
the point unless the model itself is
extraordinary.
|
> > > jeremyjh It isn't an argument, and I never said it is
better. It is an explanation for why the
pricing break is relevant. Anyone can do the
same things to take advantage of that pricing.
Would you prefer I not explain a basic fact to
someone who may not know what is possible?The
services are priced this way because larger
context has significantly higher costs. That
is a fact about the technology and it is true
for every provider. So moaning about it isn't
useful.On the other hand, there are a lot of
people who don't manage context effectively -
who start every session with 60K tokens - and
that is significantly hurting the performance
of every single thing they do with coding
agents.
|
> > > > komali2 So what's your setup? Speaking as a "open
terminal in repo, open Claude, say 'do
this thing please '" kinda guy I'm
interested in learning about these more
advanced techniques.
|
> > > > > jeremyjh I use oh-my-pi (omp.sh) - mostly with
stock settings and skills but its a
"fully loaded" harness that you don't
really have to add anything to. I do
change a couple of things: I set it to
prefer subagents, and I enable rewind.
It is crazy that rewind is not a
default, it saves a TON of context -
if the agent goes down a crazy path
that burns a lot of tokens it can
rewind to an earlier checkpoint with
the exploration or bug hunting
summary.Presently I'm using sol-high
for the default agent which does
orchestration and a lot of smaller
investigation and coding tasks itself.
sol-max for planning and review.
Luna-max for planned coding and
general tasks. I also have a $10
minimax plan and use M3 for
exploration and library roles, but I
could probably be using Luna for that
just as well and still only very
rarely run into usage issues.I don't
use any plugins or skill libraries
apart from Caveman and I'm not sure
how useful that really is anymore so
I'd start without it so you have a
baseline to compare. I do think it
reduces context usage a bit but I
haven't measured it recently. Caveman
also includes some team, agent &
investigation skills - again they
might be helping but I haven't
re-evaluated since like 90 days ago.
|
> system2 Who in their right mind would use haiku while Mimo or
GLM cost 10% of what they are charging with much
smarter models?
|
> > mrngld That's not what any benchmarks that look at cost
per task or similar says in terms of cost. The
Chinese models, generally speaking, might be
cheaper per token but need a lot more tokens to
get there.
|
> > > RussianCow Except for the new MiMo V2.6 models, which
appear to give some of the best value right
now, at least on paper. (I haven't tried them
so I can't speak from experience.)
|
> > wyrdcurt Some people/organizations are ideologically
opposed to using Chinese models. Not me, I use
GLM-5.3-Flash for almost everything (the
subscription-subsidized pricing on a legacy Z.ai
plan makes it the best value model by a wide
margin), along with some MiMo and DeepSeek. Still,
I use Luna for certain tasks where speed is more
valuable than performance; I can see this new
Haiku displacing Luna for those. If you mean Haiku
4.5 though I agree, that model was a waste of time
and money.
|
> > > pimeys Luna is not really the fastest. You need to
use it in high/max to get the good output for
what it is good for: summarizing. And that is
already close to two minutes per task...
|
> > > girvo I'm on the Legacy v2 plan and same: nothing
comes close to 5.3 Flash's value on it. It's
crazy, no wonder they discontinued them!
|
> > > RideOnTime22 There's also fomo and what I believe is
faniticism.Even for simple tasks why use X if
I know "Y Max" is available and on paper,
better?And why use something else when your
favorite company releases something. Surely it
must always be the best one to use.
|
> > > vardalab z.ai speed has been horrific, worse than
sol-6.1 was last week, I am not renewing my
sub once it expires.
|
> > nharada Isn't the point of this release that it's
comparable?AAI Index // Input // OutputHaiku 5.5:
43 // $0.10 // $0.50Mimo 2.6 Pro: 46 // $0.43 //
$0.87Mimo 2.6 Flash: 38 // $0.10 // $0.28Seems
competitive to me? Plus then I don't have to
manage multiple providers
|
> > user43928 Presumably everyone who doesn't bother integrating
a third party API key into their harness, which
would probably be most of the Claude Code users.
|
> > usef- On subscription pricing a $20 Anthropic
subscription gives >$500 equivalent tokens, which
is not so different, and you get smarter models.
API pricing has decent margins.And Opus 5.5 is
really good.
|
> > pkulak Where do you get this 10% number? Checking
providers I know/respect, and GLM 5.3 flash is
$0.15/m. Haiku is $0.10/m.
|
> > flaburgan They say it in the announcement: Haiku is
basically useful to be called as a subagent. So
you use Opus, and you want to investigate your
production logs, instead of throwing them right
away which is going to use a massive amount of
token for mostly noise data, Opus asks Haiku to
determine patterns to extract only the relevant
logs and feed it back in Opus. The models are
meant to be used together.
|
> > > walthamstow > The models are meant to be used together.If
that was the case, then Claude Code would use
smaller models for subagents. It doesn't. The
subagent always inherits the parent model
unless you tell it specifically not to.
|
> > skeledrew Well, unless you're using OpenCode Go, it's
per-token costs (even if already super low), while
Haiku falls under the Claude sub. It's just more
straight forward and you aren't feeling a "loss"
with the sub.
|
> > aesthesia There really aren't any models at 10% of the price
of Luna or Haiku.
|
> > ray_kay777 People who are stuck using Bedrock in-geo due to
their company policy (me).
|
> port3000 They are targeting businesses/API use for fast
decision making and agent integration. Plus they now
need to be competitive with Jev-type models in that
space.
|
> > cogman10 I think they are also trying to make sure Deepseek
and other chinese models don't eat their lunch.
They need something price competitive.
|
> giancarlostoro I with they'd give Haiku like 400k tokens roughly, I
think between 400k or even 600k tokens is a sweet
spot, but Haiku is basically designed to be for small
edits is my understanding, but it sucks because any
time I ask Opus to "try" letting Haiku do the work, it
just falls apart and Opus comes back and tells me it
switched to Sonnet (even before Sonnet finally jumped
up to 5.x).I will try the new Haiku, but it would be
worthwhile if Haiku could take sane instructions and
do all file editing for Opus / Sonnet / Fable then it
would be worth using.
|
> mnicky You could also use it as a subagent prompted eg by
Sonnet/Opus orchestrator agent and for many agentic
workflows significant part of the dispatched tasks
might be under 100k budget.
|
> mkotlikov If you look at how different reasoning levels can
easily exceed task cost of sonnet 5.5 you will see
that you will basically never fall into that under
100,000 token threshold. I mean maybe you can choose
low and do a basic summary task, but then you could
choose something much cheaper instead. I don't know
what Anthropic is thinking with its dumber models.
|
> dj_io Haiku doesn't seem most cost effective solution. Jev
like classifier can work in a fairly smaller model
which are 1/10 of the cost. Opus is SOTA so I get the
use case for one being restricted to Anthropic
ecosystem. I think the use case for Haiku is mainly
for users using on their chat for pro subscribers and
free users to maximize their quota.
|
> insanitybit I mostly use Haiku for really, really basic stuff,
never for actual engaging work. I've used it for
first-pass analysis to triage bugs, for example - all
it does is related N bugs together to see if any
potentially relate. Then I have Sonnet investigate
further.
|
> esafak It's their creative way of 'matching' Luna's prices.
|
> krzyk They want to get on the Luna market.If there was no
Luna you would see only the >100k pricing, but because
we have Luna, they had to lower price for something.
|
> chaostheory Going on a slight tangent, I've found that Anthropic
(for my work) costs about 4x as much as OpenAI give or
take, specifically Opus vs Astra
|
> AustinDev encode and decode tok/s which is ($/s) when it comes
to pricing drops heavily above 100k tokens.There are
plenty of workflows like translations where you'd
easily be under the cap.
|
> j45 It could be to incentivize people to not be lazy users
of tokens.
|
> sixtyj Chatbot could be < 100k tokens.
|
> solenoid0937 This is pretty good tbh
|
> judetechdevs interesting! thx for your info
|
chriddyp Ran our DataAnalyticsBench benchmark on it:
https://plotly.com/blog/claude-haiku-5-5-plotly-data-analy
ti...9x cheaper than Haiku 4.5 and 2 letter grades better.
It's also now the fastest model (using the default speeds,
not trying any of the other models "Fast" mode) to
complete the exam.Similar ballpark to Luna in price, cost,
and accuracy. These are very cheap models: $0.38 to answer
40 in-depth data analytics questions (compared to $15 for
Opus 5.5 or $20 for Astra).Overall very good at data
analysis - handling all of the straightforward data
analytics questions correctly. It fell short answering
some of the questions that required some deeper
statistical analysis like looking into other variables. In
other words, it's not as persistent as other models in its
analysis, which I think we'd expect from how they're
positioning the model.Compared to OpenAI: GPT-6 Luna did a
bit better and was about 30% the cost of Haiku 5.5.
GPT-6.1 Sol got all answers correct, but was 10x more
expensive.
|
> doktor_pepsi Appreciate providing this benchmark. I am curious, do
you think that as new models (from the same company)
are released and you repeat the benchmark, they
adapt/extend their training data to include your
dataset, thus polluting the benchmark results? Would
you be doing anything to combat this?
|
> > agentdev001 I've considered this as well, as many others have.
I tend to think that A: this is moreso a feature
rather than a bug, and B: this is almost
impossible to measure- it's a boogeyman imo.In
other words, combating this is impossible if it's
happening. Measuring whether its happening is also
not plausible, for small fish running bespoke
benchmarks suites. I think we (consumers) have hit
a pretty clear stride of; new model releases >
some subset of evals/benchmarks are saturated >
new, harder, more niche evals and benchmarks take
their place. That doesnt seem unhealthy to me.
|
> > chriddyp It's a valid concern. We're not releasing the
dataset, the answers, or the full set of questions
to help prevent this. At the same time, I like to
share where it gets things wrong in a bit more
detail, which involves sharing a bit of the exam.
I expect that we'll create a new benchmark with a
new dataset in 6 months.
|
charlesabarnes > Second, this week, we'll roll out a new monthly API
credit to all Max and Team subscribers for use on the
Claude Platform. Max 5x users will get $100 in credits per
month, Max 20x users will get $200, and Team subscribers
will receive up to $500, pooled across their usersThis is
a very big benefit for me. I can now ship actual ai
enhanced features behind my subscription without paying
extra or fully relying on on-device models. I do worry
that this is to soften the blow for user-unfriendly
changes
|
> thepasch This is them sneaking in taking the Claude Agent SDK
(claude -p) off of subscription plans through the back
door along with a model release. They previously
wanted to do this in June, but backpedaled after huge
backlash:https://support.claude.com/en/articles/150365
40-use-the-clau...
|
> > luketaylor Sorry that that help center article was
misleading; we've updated it to clarify that
`claude -p` has not been removed from
subscriptions as part of this change!
|
> > > thepasch That's super encouraging to hear, thank you
for the clarification! I'd edit my original
comment, but the edit window has unfortunately
run out on it. Should be OK, though, since the
help desk page is now explicit about it.
|
> > > arcanemachiner Are you able to speak about the degree to
which non-Claude harness use is discouraged?
Has Anthropic's disdain towards non-Claude
Code harnesses settled down since the compute
crunch + OpenClaw heydey?More importantly,
will my personal company account get banned
for using a non-Claude Code harness?Not sure
if you're able to answer these questions, but
I would appreciate it if you can.
|
> > > TomGarden I've been operating under the pretense that
claude -p was removed ages ago in the OpenClaw
era, it's back now? What a mess of
contradictory information, hope yall can
figure it out
|
> > > > scottyeager They never actually made the change. Using
-p with a subscription has worked all
along.
|
> > > > > TomGarden At one point they definitely turned it
off and gave us a one-time credit to
claim for -p, after which Claude -p
was billed as extra usage
|
> > > > > > scottyeager See:
https://support.claude.com/en/arti
cles/15036540-use-the-clau...The
change was "paused" pretty
quietly.
|
> > > AISnakeOil They changed this from earlier today...
It's still very confusing.
|
> > > > verdverm one day they might realize the importance
of reading llm output... maybe?
|
> > > > > Forgeties79 No one else does so why would they
|
> > > > > > verdverm lots of people are staying
human-in-the-loopAnthropic is
among the worst, their linux
kernel hack is a prime example,
didn't even count the "CVEs" to
see Mythos can't count
eitherhttps://www.youtube.com/watc
h?v=NnV_cWeoo5Q
|
> > > > > > Forgeties79 OpenAI just as bad with hugging
face/wikipedia
|
> > > > > > verdverm I find OAI much worse on the
negligence side, especially with
the Tumbler Ridge school
shootinghttps://www.cbc.ca/news/ca
nada/british-columbia/mother-jones
...ANT annoys me more with their
ai psychosis on steroids
|
> > > goosejuice Was it ever? I thought that whole thing was
paused. Still unclear if personal use of agent
sdk inside a harness is allowed.
|
> > > > deaux I've been using `claude -p` for personal
use for a long time without issues. I do
mean actual irregular, personal use
though. Not using it to max out my quota,
using it as main rather than sub or trying
to be cheeky with it.
|
> > > jen729w Can I build an app against this? Do you commit
to not changing it again tomorrow?
|
> > > pastel8739 But it is? Especially from Pro subscriptions,
which don't get API credits
|
> > > > eli It uses subscription quota just like
before
|
> > > tekacs Really appreciate you coming in here and
clarifying!
|
> > tekacs I hope people notice again that this is happening
this time around.Being forced through the non-OSS
Claude Code with all of its quirks and issues
is... such an exhausting use of force by
Anthropic.To the extent that you _can_ choose to
disable telemetry and training on your traces in
CC, it's not all that obvious what they gain by
crippling your ability to use the subscription
with other - better - tools.It's also remarkable
that it's coincident with OpenAI adding "Sign in
with OpenAI", so that you can use your tokens with
other tools.
|
> > eli The page does not say anything about changing the
way Agent SDK bills. I just tested Agent SDK and
nothing has changed (yet).You might be right and
they will change this in the future, but that's
speculative
|
> > > thepasch > Claude Max and Team plans now include
monthly API credits, which cover the Claude
Agent SDK, the Claude API, and Claude Managed
Agents.This text has replaced the entirety of
the page called "Use the Claude Agent SDK with
your Claude plan."
|
> > > > eli Yes. Previously the page was all about how
they were going to start charging for
Agent SDK use with a banner on the top
saying that, actually, they weren't going
to do that.
|