[tedivm]

Something similar is happening with GitHub Copilot too. It's impossible to know what a "request" is and some change in the last couple of months has seen my request usage go up for the same style of work. Toss in the bizarre and impossible to understand rate limiting that occurs with regular usage and it's pretty obvious that these companies are struggle to scale.

[rnadomvirlabe]

I find copilot to be much more straightforward, and I can track per request against my credits. Here is the explanation of what a request is:

https://docs.github.com/en/copilot/concepts/billing/copilot-...

[tedivm]

> A request is any interaction where you ask Copilot to do something for you—whether it's generating code, answering a question, or helping you through an extension. Each time you send a prompt in a chat window or trigger a response from Copilot, you're making a request. For agentic features, only the prompts you send count as premium requests; actions Copilot takes autonomously to complete your task, such as tool calls, do not. For example, using /plan in Copilot CLI counts as one premium request, and any follow-up prompt you send counts as another.

This clearly isn't true for agentic mode though. This document is extremely misleading. VSCode has the `chat.agent.maxRequests` option which lets you define how many requests an agent can use before it asks if you want to continue iterating, and the default is not one. A long running session (say, implementing an openspec proposal) can easily eat through dozens of requests. I have a prompt that I use for security scanning and with a single input/request (`/prompt`) it will use anywhere between 17 and 25 premium requests without any user input.

[0xffff2]

Do you have any evidence to support your claims? I keep a pretty close eye on my usage and have never seen it deviate from "1x/3x requests per time I hit enter". Is there a reproducible scenario I can try that will charge multiple requests for a single prompt?

[alienbaby]

I'm finding the oppostire with copilot. A request is a prompt, with some caveats around whats generating the prompt. I am quite happily working with opus 4.6 at 3x cost and about 1/3 oor the month in I'm stting at ~25% usage of a pro+ subscription. I find it quite easy to track my usage and rate of usage.

The overall context windows are smaller with copilot I believe, but it dfoesnt appear to be hurting my work.

I'm using it for approx 4 hours a day most days. Generally one shotting fun ideas I thoroughly plan out in planning mode first, and I have my own verison of the idea->plan->analyse-> document implementation phases -> implement via agent loop. simulations, games, stuff-im-curious about and resurrecting old projects that never really got off the ground.