StepFun 3.5 Flash is #1 cost-effective model for OpenClaw tasks (300 battles)

Re:StepFun 3.5 Flash is #1 cost-effective model for OpenClaw... by sunaookami on Wednesday April 01, 2026 @02:54PM (#47604963)

Tried the free version on OpenRouter with pi.dev and it's competent at tool calling and creative writing is "good enough" for me (more "natural Claude-level" and not robotic GPT-slop level) but it makes some grave mistakes (had some Hanzi in the output once and typos in words) so it may be good with "simple" agentic workflows but it's definitely not made for programming nor made for long writing.

[ Parent | on HN ]

Re:StepFun 3.5 Flash is #1 cost-effective model for OpenClaw... by skysniper on Wednesday April 01, 2026 @03:13PM (#47605186)

it's actually pretty good at openclaw type of tasks for non technical users: lots of tool calls, some simple programing

[ Parent | on HN ]

Re:StepFun 3.5 Flash is #1 cost-effective model for OpenClaw... by sunaookami on Wednesday April 01, 2026 @04:24PM (#47606075)

Yeah this kind of stuff. I have no experience with OpenClaw though.

[ Parent | on HN ]

Re:StepFun 3.5 Flash is #1 cost-effective model for OpenClaw... by admiralrohan on Wednesday April 01, 2026 @05:09PM (#47606600)

What kind of creative writing are you doing? Fiction or non-fiction like blog posts?

[ Parent | on HN ]

Re:StepFun 3.5 Flash is #1 cost-effective model for OpenClaw... by sunaookami on Thursday April 02, 2026 @04:38AM (#47611632)

Fiction. One of my "benchmarks" is giving the model a bunch of (self-made) text and having it simulate a 4chan thread about it. This tests tool use (calling the APIs), some skills, censorship and general creativity. Some models refuse every new turn after reading real 4chan threads ;) Claude is especially good at this surprisingly while GPT fails spectacularly and Gemini is just lazy (and barely usable since it's constantly overloaded). Qwen (coder-model from Qwen CLI, so Qween 3.5) is also very good but sadly not usable in Pi (they detect and block calls outside their CLI).

[ Parent | on HN ]

Re:StepFun 3.5 Flash is #1 cost-effective model for OpenClaw... by admiralrohan on Thursday April 02, 2026 @02:05PM (#47617986)

Interesting. Are you running something like Autoresearch loop for writing fiction? How will the agent determine whether the output is good as this is subjective.

[ Parent | on HN ]

Re:StepFun 3.5 Flash is #1 cost-effective model for OpenClaw... by sunaookami on Friday April 03, 2026 @04:00AM (#47624238)

I don't have any advanced setup, creative writing is always subjective. I just one-shot most of the time.

[ Parent | on HN ]