Step Audio R1.5

Language StepFun Partly verified

Step-Audio-R1.5 is StepFun’s audio reasoning model for extended spoken conversations, designed to preserve natural prosody and emotional continuity. It uses reinforcement learning from human feedback to align audio reasoning with preferences for spoken interaction. Summary written by AI Index from StepFun’s own pages.

  • Reasoning

Prices

2 offerings · prices as listed
StepFun API (opens in a new tab) Official Global · USD step-audio-r1.5
Conditions/ 1M tokensInputCache readOutput
Standard $1.43$0.29$15.00

Prices from StepFun: pricing details (opens in a new tab) (checked Nov 4, 2026)

StepFun API (opens in a new tab) Official China · CNY step-audio-r1.5
Conditions/ 1M tokensInputCache readOutput
Standard ¥10.00¥2.00¥105.00

Prices from 阶跃星辰:定价明细 (opens in a new tab) (checked Nov 3, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Family
step-audio
Model ID

Not stated on StepFun’s pages: max input, input modalities, output modalities, reasoning efforts, reasoning can be off, max thinking budget, tool use, structured output, built-in tools, knowledge cutoff, aliases.

Cited scores

From third-party leaderboards, not measured by us

This model isn’t on any leaderboard we cite yet.

  1. Now priced on StepFun API Input $1.43 · Cache read $0.29 · Output $15.00

Sources

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

StepFun · China · stepfun.com

Snapshots, the same family and other models from this provider