Step 3.7 Flash
by StepFuntext+image+video->text3 endpoints
Neura Intelligence Index
46.5/ 100
Rank
#193—
Confidence
lowBenchmarks
1(3% coverage)
Overview
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Capabilities
Text generation
Image understanding
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities
Modalities
Input
TextImageVideo
Output
Text
Technical Specifications
Context Window
262.1K tokens
Max Output
230.4K tokens
Tokenizer
Other
Uptime (24h)
9996.5%
Parameters
198000000000B
License
apache_2_0Open Weights
Country
🇨🇳CN
Release Date
June 10, 20263mo
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Performance Over Time
Pricing
Per 1M tokens
Input$0.20
Output$1.15
Cache read$0.04
Added
May 28, 2026
Last synced 9/20/2026