待翻译：AI costs how much? GitHub Copilot users react to new usage-based pricing system

AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。

The precise number of Copilot credits used by a given prompt is determined by the number of input and output tokens used and the rates charged by the underlying large language model. That means pricing is highly dependent not just on the type of request but on the specific model that a user chooses. One million output tokens from OpenAI’s GPT-5.4 nano would run just $1.25 on GitHub Copilot, but that same level of output would run $30 on the frontier GPT-5.5 model (Copilot users who rely on “Auto” mode to pick the most appropriate available model for any request should be extremely careful, as some users report it can switch to expensive models for extremely simple queries). How much for that prompt in the window? Spot testing by Ars Technica found that re-running our simple “build a Minesweeper game” prompt through Claude Haiku 4.5 via Copilot used about 94 credits (you can view the results here). That’s a pretty decent rate for a relatively simple toy project. But it’s also easy to see how those kinds of costs could balloon quickly for requests involving major changes or reviews on complex codebases. You can see that kind of ballooning cost in reports of a single complex prompt burning through 171 Copilot credits, or another spending 700 credits on “a few prompts,” or a couple of Copilot-led commits using up 5,000 credits. Other Copilot users expressed surprise at just how many credits could be spent on even simple Copilot requests, from a reported 15 credits for a simple “run-of-the-mill query” to spending 100 credits in “generating a small plan.”