• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Token limits and credit costs in AI-dependent workflows

    One AI user says waiting for token resets is stalling work after they rebuilt systems around frontier models. They also report that £150 in Opus 5 fast credits disappeared in less than a minute.

    Kevin Patrick MurphyKP
    Machine Learning Street TalkML
    2 Sources, ,

    TLDR

    One user describes regretting building so many systems around AI, saying those systems now depend on continued access to frontier models. They report exhausting a reset Fable allowance in about an hour, then buying £150 in credits to finish the job with Opus 5 fast. Those credits were consumed in less than a minute, they say, prompting them to ask whether it was a bug. They also say Astra’s weekly subscription allowance lasts about two hours—three if they’re lucky.

    Combined views

    6K

    2 Sources, first seen 20d ago

    Combined views

    6K

    2 Sources, first seen 20d ago

    78 likes
    20d ago
    first seen 20d ago
    78 likes
    29 comments
    17 saves
    15 reposts
    29 comments
    17 saves
    15 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    Machine Learning Street Talk@MLStreetTalkLate 2026 will be remembered as the most excruciating period in AI progress, when OpenAI and Anthropic basically had us over a barrel. It's so demoralising waiting for the tokens to reset just to be able to get any work done. I'm starting to think I made a massive error building so many systems on top of AI. During the times of token abundance, we rearchitected everything to use AI, now in the dark times we are utterly dependent and desperate. It's practically impossible to get anything serious done without frontier tokens, not least of which because using the frontier models even for a short time creates psychological dependency and complexifies our systems to the degree that requires their continued usage. They hooked us on their product, then started turning the screws. My Fable usage (finally) reset on one account, that was single-shot gone in about 1 hour. Left in a bad state, so I purchase £150 of credits to finish the job in Opus 5 fast (normal Opus is intolerably slow, like watching paint dry). That was then eaten up in less than 1 minute?! @bcherny ?? Bug?! Using subscriptions at frontier-level has basically become impossible, Astra/Fable API prices are a joke (£100 every 10 mins), and there are no decent alternatives or competition. Now I don't even trust Anthropic to purchase more fast Opus tokens. Astra is basically unusable too @thsottiaux, a weekly subscription drained in about 2 hours (3 if I am lucky). No more pro accounts. No more resets either. I can't even use AI on my phone now, because - guess what. Out of tokens everywhere! None of my remote stuff works because I always have to juggle different accounts on different servers, and don't even have enough tokens to wire it up again. Everything is broken, and a total disaster. As for "automation", what's the point in automation if you can't do anything for more than an hour before it craps out and leaves you in a bad state?! I have tried the alternative models like Muse 1.3, Gemini 3.8, Grok etc, nothing even comes close and they would probably do more harm than good in the codebase. Contra "pace" - it's never been more important to accelerate AI competition and progress. It's a defacto cartel at this point, little wonder they want to maintain the status quo. This situation is intolerable. We were building for a future that we thought would have arrived by now, and here we are - frankly, up shit creek without a paddle.20d
    Kevin Patrick Murphy@sirbayes@MLStreetTalk I haven't dared yet try Astra, for fear I will (1) run out of tokens, (2) not want to go back to Sol (which is working fine for me). I am using LLM coding agents to generate "classical" ML code that rarely needs an LLM at run time.20d

    2 Sources

    Machine Learning Street Talk@MLStreetTalkLate 2026 will be remembered as the most excruciating period in AI progress, when OpenAI and Anthropic basically had us over a barrel. It's so demoralising waiting for the tokens to reset just to be able to get any work done. I'm starting to think I made a massive error building so many systems on top of AI. During the times of token abundance, we rearchitected everything to use AI, now in the dark times we are utterly dependent and desperate. It's practically impossible to get anything serious done without frontier tokens, not least of which because using the frontier models even for a short time creates psychological dependency and complexifies our systems to the degree that requires their continued usage. They hooked us on their product, then started turning the screws. My Fable usage (finally) reset on one account, that was single-shot gone in about 1 hour. Left in a bad state, so I purchase £150 of credits to finish the job in Opus 5 fast (normal Opus is intolerably slow, like watching paint dry). That was then eaten up in less than 1 minute?! @bcherny ?? Bug?! Using subscriptions at frontier-level has basically become impossible, Astra/Fable API prices are a joke (£100 every 10 mins), and there are no decent alternatives or competition. Now I don't even trust Anthropic to purchase more fast Opus tokens. Astra is basically unusable too @thsottiaux, a weekly subscription drained in about 2 hours (3 if I am lucky). No more pro accounts. No more resets either. I can't even use AI on my phone now, because - guess what. Out of tokens everywhere! None of my remote stuff works because I always have to juggle different accounts on different servers, and don't even have enough tokens to wire it up again. Everything is broken, and a total disaster. As for "automation", what's the point in automation if you can't do anything for more than an hour before it craps out and leaves you in a bad state?! I have tried the alternative models like Muse 1.3, Gemini 3.8, Grok etc, nothing even comes close and they would probably do more harm than good in the codebase. Contra "pace" - it's never been more important to accelerate AI competition and progress. It's a defacto cartel at this point, little wonder they want to maintain the status quo. This situation is intolerable. We were building for a future that we thought would have arrived by now, and here we are - frankly, up shit creek without a paddle.20d
    Kevin Patrick Murphy@sirbayes@MLStreetTalk I haven't dared yet try Astra, for fear I will (1) run out of tokens, (2) not want to go back to Sol (which is working fine for me). I am using LLM coding agents to generate "classical" ML code that rarely needs an LLM at run time.20d

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.