Integrate multimodal vision capabilities using Stepfun/Step-3.5 Flash, designed to process both text and images seamlessly. This model delivers available completely free of charge. Access Stepfun/Step-3.5 Flash via the Qiniu API with up to 4K output tokens.
Tokens
Tokens
Tokens
Stepfun/Step-3.5 Flash by Qiniu costs Free per 1M input tokens and Free per 1M output tokens.