Integrate multimodal vision capabilities using stepfun-ai/step3, designed to process both text and images seamlessly. This model delivers cost-effective pricing at $0.57/1M input and $1.42/1M output tokens, native tool calling support. Access stepfun-ai/step3 via the SiliconFlow API with up to 66K output tokens.
Tokens
Tokens
Tokens
stepfun-ai/step3 by SiliconFlow costs $0.57 per 1M input tokens and $1.42 per 1M output tokens.