跳过导航
DeepSeek v4.1 Flash via API is almost TOO fast 🤯
0:00 / 0:21

DeepSeek v4.1 Flash via API is almost TOO fast 🤯

Mia

@MiaAI_lab4.6万 位关注者

在 X 上查看
1,190 个赞下载原帖

139,524 次观看

DeepSeek v4.1 Flash via API is almost TOO fast 🤯

46 条评论

评论来自 X (Twitter) 上的原帖

  • keys 🧪 的头像

    @u1tra_instinct

    Actually don’t want the model to run too fast then you have keep scrolling up to see what happened it’s annoying after a while

    38 个赞

  • Mia 的头像

    @MiaAI_lab

    Good problem to have imo

    60 个赞

  • hkdom 的头像

    @hkdom

    You will wow more if you run it with DSH

    16 个赞

  • Mia 的头像

    @MiaAI_lab

    You're probably right

    5 个赞

  • Santanu Sinha 的头像

    @santanu_sinha

    Genuine question.. what harness is that and why is it flickering so much? Also .. yes amazing speed

    8 个赞

  • Mia 的头像

    @MiaAI_lab

    Hermes agent CLI

    10 个赞

  • Santanu Sinha 的头像

    @santanu_sinha

    Ok thanks

  • kaith 的头像

    @kaithx01

    How’s it’s performance?

    6 个赞

  • Mia 的头像

    @MiaAI_lab

    Looking better than v4 flash

    25 个赞

  • Consigliere 的头像

    @seree

    via Cloud API?

    4 个赞

  • Mia 的头像

    @MiaAI_lab

    Yes

    4 个赞

  • Gaurav Bhatia 的头像

    @heygauravbhatia

    Imagine after thinking for that long it doesn’t complete the work.

    3 个赞

  • Mia 的头像

    @MiaAI_lab

    But it did 😀

    1 个赞

  • Wassollichhier 的头像

    @wassollichhier

    is vision onboard?

    2 个赞

  • Mia 的头像

    @MiaAI_lab

    Not on this one, it's beta

    2 个赞

  • Samuel McHargue 的头像

    @hotredsam

    @grok how much is v4.1 flash compared to the older one.

    2 个赞

  • Bear 的头像

    @BearHuddleston

    Vision support?

    2 个赞

  • Daniel Carneiro 的头像

    @iamloonix

    WTF is that ugly TUI?

    2 个赞

  • nah 的头像

    @nahcmonpls

    Imagine every model being this fast. That'd be amazing.

    2 个赞

  • Steven Cheng 的头像

    @stevencheng

    Latency that low feels like cheating.

    1 个赞