Huawei token plan is quite expensive
Not cheap, especially the way token consumption is counted—both input and output are counted within the plan. I often use 20 million tokens in a single request, and the 59 yuan tier only covers about 3 of my requests. For coding, roughly 99% of input is input cache, and billing cache hits at full price is pretty absurd. If they want people to actually use it, they shouldn’t count input—only count output toward the quota,…
Categories:
Not cheap, especially the way token consumption is counted—both input and output are counted within the plan. I often use 20 million tokens in a single request, and the 59 yuan tier only covers about 3 of my requests. For coding, roughly 99% of input is input cache, and billing cache hits at full price is pretty absurd. If they want people to actually use it, they shouldn’t count input—only count output toward the quota, then it’s worth considering. Take Alibaba Cloud’s token plan for example: at least it distinguishes between input and input cache, with cache hit priced at 1/10, which is some discount. Not sure whether Huawei simply has no cache hits, or the docs just forgot to mention it.
