We notice with frontier models like Astra and Fable that one might use a lot less tokens than the other to complete the task thereby being the better deal in spite of the far higher token cost.
Astra on xhigh has a cost per task of $2.31 with an intelligence index of 53. Qwen3.8 Max has a cost per task of $5.41 with an intelligence index of 45. Pricing for GPT-6 Astra (xhigh) is $10.00 per 1M input tokens and $50.00 per 1M output tokens. Pricing for Qwen3.8 Max (0902) is $2.00 per 1M input tokens and $6.00 per 1M output tokens.
Obviously this is just one measure of all of this (and Qwen 3.8 Omni Flash isn't yet available), but I think this illustrates the point well. These relative task costs are pretty consistent across different analysts. Cost per token is arguably a useless measure at this point in most circumstances.
On some benchmarks models like Qwen 3.8 Max which cost < $6/m out cost more than Astra 6 to run at $50/m out. That’s a huge price gap and yet Astra would be cheaper if your work looks like the benchmark.
Yes, for fun I tried OVH AI Endpoint and they do not have cache read at all. They bill you every time you send a prompt regardless if you are hit cache or not. One agent session was like 80M input and 300K output and I paid 30$ for that. Or rather I interrupted it and let my local Qwen finish it because cost was getting radicoulous.
If Gemini can complete a task for $1 and Qwen completes that same task for $1, then the cost per token is irrelevant in most use-cases. One would think this stuff should correlate well enough that you can use it as a proxy, but I think a lot of people are noticing this is a serious mistake and that these "cheap" models aren't as cheap as they appear when you consider this.
You point is valid for textual LLM, with large CoT, not Omni which will respond quick with a voice. In this case, token price is a good enough proxy.
What matter the most and isn't told by token price is the latency. You expect a voice LLM to respond very quick. If it takes 5s to response to a simple "Hello, what the weather today?", them not much people will use it.
_ache_ · · focus · HN ↗
in/out ($) Gemini : 1.5 / 9.0 | Qwen 3.8: 0.15 / 0.47
That is a massive cost reduction.
Refs: <a href="https://www.alibabacloud.com/help/en/model-studio/model-pricing#china-beijing-h4" rel="nofollow">https://www.alibabacloud.com/help/en/model-studio/model-pric... <a href="https://runware.ai/gemini-omni" rel="nofollow">https://runware.ai/gemini-omni
killingtime74 · · focus · HN ↗
vntok · · focus · HN ↗
kaliqt · · focus · HN ↗
LeBit · · focus · HN ↗
Even if OpenAI end up using 1 token for per task, if the token costs 1M$ , some people will find it expensive.
nater5000 · · focus · HN ↗
Astra on xhigh has a cost per task of $2.31 with an intelligence index of 53. Qwen3.8 Max has a cost per task of $5.41 with an intelligence index of 45. Pricing for GPT-6 Astra (xhigh) is $10.00 per 1M input tokens and $50.00 per 1M output tokens. Pricing for Qwen3.8 Max (0902) is $2.00 per 1M input tokens and $6.00 per 1M output tokens.
Obviously this is just one measure of all of this (and Qwen 3.8 Omni Flash isn't yet available), but I think this illustrates the point well. These relative task costs are pretty consistent across different analysts. Cost per token is arguably a useless measure at this point in most circumstances.
alphabettsy · · focus · HN ↗
tidbeck · · focus · HN ↗
npodbielski · · focus · HN ↗
_ache_ · · focus · HN ↗
nater5000 · · focus · HN ↗
If Gemini can complete a task for $1 and Qwen completes that same task for $1, then the cost per token is irrelevant in most use-cases. One would think this stuff should correlate well enough that you can use it as a proxy, but I think a lot of people are noticing this is a serious mistake and that these "cheap" models aren't as cheap as they appear when you consider this.
_ache_ · · focus · HN ↗
What matter the most and isn't told by token price is the latency. You expect a voice LLM to respond very quick. If it takes 5s to response to a simple "Hello, what the weather today?", them not much people will use it.