StepFun models, pricing, and protocols

2 currently available models with pricing synced from the MoleAPI console.

2 models

Compare

step-3.5-flash-90%

StepFun model by StepFun for general chat, writing, coding assistance, and tool-assisted workflows.

Success: 0.0%
Avg latency: 439ms

View model

defaultx1

Input$0.1 / 1M tokens

Output$0.3 / 1M tokens

Cache read$0.02 / 1M tokens

tempx0.1

Input$0.01 / 1M tokens

Output$0.03 / 1M tokens

Cache read$0.002 / 1M tokens

openaiopenai-responseopenai-response-compactanthropicgeminiopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare

step-3

StepFun model by StepFun for general chat, writing, coding assistance, and tool-assisted workflows.

View model

defaultx1

Input$0.21 / 1M tokens

Output$0.63 / 1M tokens

openaiOpenAI compatibleCompare