Comment by jen729w 15 days ago Or a 3rd party service like https://synthetic.new, of which I am an unaffiliated user. 2 comments jen729w Reply cmrdporcupine 15 days ago So, Deepseek 3.1 from their own platform:Input $0.28 / 1M tokens cache miss Output $0.42 / 1M tokensVia synthetic (which otherwise looks cool):Input $0.56/mtok Output $1.68/mtokSo 2-3 better value through https://platform.deepseek.com(Granted Synthetic gives you way more models to choose from, including ones that don't parrot CPC/PLA propaganda and censor) ojosilva 14 days ago I'm using CC + GLM 4.6 from Synthetic and results are top notch for $60/mo, speed is fast and servers are close to home than z.ai
cmrdporcupine 15 days ago So, Deepseek 3.1 from their own platform:Input $0.28 / 1M tokens cache miss Output $0.42 / 1M tokensVia synthetic (which otherwise looks cool):Input $0.56/mtok Output $1.68/mtokSo 2-3 better value through https://platform.deepseek.com(Granted Synthetic gives you way more models to choose from, including ones that don't parrot CPC/PLA propaganda and censor)
ojosilva 14 days ago I'm using CC + GLM 4.6 from Synthetic and results are top notch for $60/mo, speed is fast and servers are close to home than z.ai
So, Deepseek 3.1 from their own platform:
Input $0.28 / 1M tokens cache miss Output $0.42 / 1M tokens
Via synthetic (which otherwise looks cool):
Input $0.56/mtok Output $1.68/mtok
So 2-3 better value through https://platform.deepseek.com
(Granted Synthetic gives you way more models to choose from, including ones that don't parrot CPC/PLA propaganda and censor)
I'm using CC + GLM 4.6 from Synthetic and results are top notch for $60/mo, speed is fast and servers are close to home than z.ai