-- Stronger model from claude subscription is responsible for analysis/solution design/task creation.
-- Cheaper model (qwen3.6, local deployment on 36GB GPU with 250K context size) is responsible for task execution
Doing this for less then 24 hours. Fable can monitor and validate execution and create smaller tasks when something has to be adjusted after qwen execution. It is slower ofc, but this can work non stop without hitting the limits even when using Fable for orchestration/monitoring. Using this app for orchestration: https://github.com/sermakarevich/fleet
There are other reasons why the roles separation might be important. Anthropic changes limits for claude -p next Monday. But even current limits are not great - they might be ok for occasional research but they burn within 2 hour of coding in interactive mode and 20 minutes if we use multiple workers. There are rumors that tokens we got within subscription fee for $200 is equivalent to 8-12K in API cost.
Question is what companies will do when subscription fee will be not enough even for coding. Paying x40 does not look like an option.
I built a Claude Code tracker that specifically tracks this for me now, and shows me what I would be spending when this isn't included after the 22nd of June. Its going to take an adjustment to these new pricing model changes with Claude, with Agent and SDK going credit based on the 15th as well. My tracker tracks both. Hit me up if you want the info on it, its open source and available to all.
-- Stronger model from claude subscription is responsible for analysis/solution design/task creation.
-- Cheaper model (qwen3.6, local deployment on 36GB GPU with 250K context size) is responsible for task execution
Doing this for less then 24 hours. Fable can monitor and validate execution and create smaller tasks when something has to be adjusted after qwen execution. It is slower ofc, but this can work non stop without hitting the limits even when using Fable for orchestration/monitoring. Using this app for orchestration: https://github.com/sermakarevich/fleet
There are other reasons why the roles separation might be important. Anthropic changes limits for claude -p next Monday. But even current limits are not great - they might be ok for occasional research but they burn within 2 hour of coding in interactive mode and 20 minutes if we use multiple workers. There are rumors that tokens we got within subscription fee for $200 is equivalent to 8-12K in API cost.
Question is what companies will do when subscription fee will be not enough even for coding. Paying x40 does not look like an option.