Comment by amclennon 16 hours ago It looks like this also undercuts the already absurdly inexpensive Deepseek Flash in pricing. Wild. 8 comments amclennon Reply geooff_ 16 hours ago Where are you seeing that? At the bottom of this post from Qwen I see:Qwen 3.8 flash: $0.16 / $0.47Compared toDeepseek 0723: $0.03 / $0.075(units in USD/m tok) twohaibei 16 hours ago 0.03 / 0.075 ? Where can i get that prices? Especially during peak hours DS4flash became much more money hungry than last month.https://api-docs.deepseek.com/quick_start/pricing kaelwd 15 hours ago https://openrouter.ai/deepseek/deepseek-v4-flash-0731?endpoi...8t/s though apparently and their cache hit rate is terrible so I don't think it's worth it over Relace. ls_stats 16 hours ago Deepseek 0732 is $0.22/$0.66 off peak water-drummer 9 hours ago GLM-5.3-Flash which is larger and better, costs less than this kzrdude 16 hours ago (Edited: I thought Qwen3.8 Flash Next was smaller, but it's not, in bytes. Here's how they compare.)DSV4 Flash 304B params, 167 GB download (at full size)Qwen3.8 Flash Next 180B params, 360 GB download (at full size) dalant979 15 hours ago 180B? kzrdude 15 hours ago 125B regular params, 51B engrams, 4B MTP. Something like that. It should have a label of effectively 125B params with A6B (6B active).
geooff_ 16 hours ago Where are you seeing that? At the bottom of this post from Qwen I see:Qwen 3.8 flash: $0.16 / $0.47Compared toDeepseek 0723: $0.03 / $0.075(units in USD/m tok) twohaibei 16 hours ago 0.03 / 0.075 ? Where can i get that prices? Especially during peak hours DS4flash became much more money hungry than last month.https://api-docs.deepseek.com/quick_start/pricing kaelwd 15 hours ago https://openrouter.ai/deepseek/deepseek-v4-flash-0731?endpoi...8t/s though apparently and their cache hit rate is terrible so I don't think it's worth it over Relace. ls_stats 16 hours ago Deepseek 0732 is $0.22/$0.66 off peak water-drummer 9 hours ago GLM-5.3-Flash which is larger and better, costs less than this
twohaibei 16 hours ago 0.03 / 0.075 ? Where can i get that prices? Especially during peak hours DS4flash became much more money hungry than last month.https://api-docs.deepseek.com/quick_start/pricing kaelwd 15 hours ago https://openrouter.ai/deepseek/deepseek-v4-flash-0731?endpoi...8t/s though apparently and their cache hit rate is terrible so I don't think it's worth it over Relace.
kaelwd 15 hours ago https://openrouter.ai/deepseek/deepseek-v4-flash-0731?endpoi...8t/s though apparently and their cache hit rate is terrible so I don't think it's worth it over Relace.
kzrdude 16 hours ago (Edited: I thought Qwen3.8 Flash Next was smaller, but it's not, in bytes. Here's how they compare.)DSV4 Flash 304B params, 167 GB download (at full size)Qwen3.8 Flash Next 180B params, 360 GB download (at full size) dalant979 15 hours ago 180B? kzrdude 15 hours ago 125B regular params, 51B engrams, 4B MTP. Something like that. It should have a label of effectively 125B params with A6B (6B active).
dalant979 15 hours ago 180B? kzrdude 15 hours ago 125B regular params, 51B engrams, 4B MTP. Something like that. It should have a label of effectively 125B params with A6B (6B active).
kzrdude 15 hours ago 125B regular params, 51B engrams, 4B MTP. Something like that. It should have a label of effectively 125B params with A6B (6B active).
Where are you seeing that? At the bottom of this post from Qwen I see:
Qwen 3.8 flash: $0.16 / $0.47
Compared to
Deepseek 0723: $0.03 / $0.075
(units in USD/m tok)
0.03 / 0.075 ? Where can i get that prices? Especially during peak hours DS4flash became much more money hungry than last month.
https://api-docs.deepseek.com/quick_start/pricing
https://openrouter.ai/deepseek/deepseek-v4-flash-0731?endpoi...
8t/s though apparently and their cache hit rate is terrible so I don't think it's worth it over Relace.
Deepseek 0732 is $0.22/$0.66 off peak
GLM-5.3-Flash which is larger and better, costs less than this
(Edited: I thought Qwen3.8 Flash Next was smaller, but it's not, in bytes. Here's how they compare.)
DSV4 Flash 304B params, 167 GB download (at full size)
Qwen3.8 Flash Next 180B params, 360 GB download (at full size)
180B?
125B regular params, 51B engrams, 4B MTP. Something like that. It should have a label of effectively 125B params with A6B (6B active).