stepaudio-2.5-chat

Operational
Audio
Reasoning
Tools

Standard & Paid Price

Standard Price
MeterStandard Price
Input price$1.5000 / 1M tokens
Completion price$3.5000 / 1M tokens
Cache read price$0.3000 / 1M tokens
Billing details
Vendor list price comparison

Description

StepFun StepAudio 2.5 Chat — end-to-end speech understanding model: it takes audio or text in and returns text, reading paralinguistic signal such as hesitation and laughter from the waveform itself rather than from a transcript. Supports extensive persona customization covering character, speech habits, and emotional range. Audio is supplied as input_audio content parts on the chat completions endpoint. For spoken replies use a TTS model.

Capabilities

Tasks
chat, reasoning, audio-understanding

API endpoints

  • POST /v1/chat/completions (openai)
  • POST /v1/messages (anthropic)