ModelInfo
English
All models

Step-1o Turbo Vision

Vision model for image and video understanding.

StepFunstep-1o-turbo-visionReport incorrect data

Specs

Context
32.8K
Max output
—
Input price
$0.36/ 1M tokens
Output price
$1.15/ 1M tokens
Released
—

Context

Context window
32.8K
Max input
—
Max output
—

Pricing · USD / 1M tokens

Input
$0.36
Output
$1.15
Cache read
$0.07
Cache write
—

Modalities

Input
TextImageVideo
Output
Text

API

API types
chat

Reasoning

Not published

Info

Status
Active
Released
—
Knowledge cutoff
—

Features

Not published
Source · official docsVerified 2026-10-10

How to call

1 provider

stepfunmodel = step-1o-turbo-vision

chat
POSThttps://api.stepfun.ai/v1/chat/completions

JSON

Standard format
step-1o-turbo-vision.json
{
  "id": "step-1o-turbo-vision",
  "object": "model",
  "created": null,
  "owned_by": "stepfun",
  "name": "Step-1o Turbo Vision",
  "api": {
    "types": [
      "chat"
    ]
  },
  "limits": {
    "context": 32768,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_tokens",
    "input": 0.36,
    "output": 1.15,
    "cache_read": 0.07,
    "cache_write": null
  },
  "features": [],
  "info": {
    "status": "active",
    "release_date": null,
    "knowledge_cutoff": null,
    "description": "Vision model for image and video understanding.",
    "docs": "https://platform.stepfun.ai/docs/en/guides/models/vision",
    "verified_at": "2026-10-10"
  }
}

Official sources

3