LLM Reference

Step-1.5V

ProprietaryMultimodal

About

Step-1.5V is StepFun's multimodal language model with vision capabilities, building on Step-1 with image understanding.

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
StepFun APIServerless

Specifications

FamilyStep
Released2024-06-01
Context128K
ArchitectureDecoder Only
Specializationgeneral
LicenseProprietary