Stepfun models
All 3 Stepfun models on OpenDunes, priced in Algerian Dinars.
Models3
Understands
TextImagesVideo
Replies with
Text
↑33,28 – 332,84 DA/ 1M tokens
↓99,85 – 898,66 DA/ 1M tokens
Context up to1M
All 3 Stepfun models on OpenDunes, priced in Algerian Dinars.
Step 5 Preview reads text, pictures and video and writes text, keeping about 1,000 pages in mind at once. StepFun calls it its flagship for long tasks: it does well at building software and at expert office work, finance above all, across big codebases and document sets, where it uses tools and refines its result step by step.
Step 3.7 Flash reads text, pictures and video and writes text, keeping about 260 pages in mind at once. You pick a high, medium or low thinking level to trade speed and cost against depth. StepFun designs it for coding, long jobs that use connected tools, filling in the exact tables you specify, and long-document work.
Step 3.5 Flash reads and writes text, thinks before it answers, and keeps about 260 pages in mind at once while staying fast on long inputs. StepFun calls it its most capable open model, released under the Apache 2.0 licence so you can download it and run it yourself, and it supports connected tools for agent work.