Step 3.7 Flash
StepFun's flagship multimodal reasoning model, a 198B total parameter sparse MoE with 11B active parameters. Natively understands images and video, supports adjustable reasoning effort, and is optimized for agent and coding workflows with reliable tool calling.
- Type
- Multimodal
- Weights
- Closed
- Downloads
- 22k
- Likes
- 455
- Pipeline
- image text to text
- License
- apache-2.0
Model hub
stepfun-ai/Step-3.7-Flash
- Repo
- stepfun-ai/Step-3.7-Flash
- Library
- transformers
- Access
- Public
Technical tags and languages
More from StepFun
9
-
ACE Step v1.5
Audio
ACE-STEP v1.5 is an open source, super fast music foundation model that uses a hybrid language model plus dif…
-
ACE-Step 1.5 XL (4B DiT)
Multimodal
ACE-Step 1.5 XL is the 4B-parameter Diffusion Transformer decoder in the ACE-Step 1.5 music generation line,…
-
146k DL
Step 3.5 Flash
Text
Step 3.5 Flash is StepFun’s open source sparse MoE LLM, with 196B total parameters but 11B active per token,…
-
Step Image Edit 2
Multimodal
Step Image Edit 2 is StepFun’s lightweight unified image generation and editing model. It supports both text-…
-
4.1k DL
Step-Audio-EditX
Audio
Step-Audio-EditX is a text-guided audio editor for speech, music, and effects. Describe the change and it per…
-
StepAudio 2.5 TTS
Multimodal
StepAudio 2.5 TTS is StepFun’s contextual text-to-speech model with performance-oriented vocal control. It co…
About StepFun
1
StepFun AI is a creative AI assistant platform that offers chat, search, coding help, and multimodal generation (images, audio, video), plus research models like Step3 and NextStep-1.