stepfunVision

StepFun: Step 3.7 Flash

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

Context
256k tokens
Input / 1M tokens
$0.20
Output / 1M tokens
$1.15
Benchmark

Pricing

Input tokens$0.20 per 1M tokens
Output tokens$1.15 per 1M tokens
Cache read$0.04 per 1M tokens

Technical details

Model IDstepfun/step-3.7-flash
Context window256k tokens
Input modalitiestext, image, video
Output modalitiestext
TokenizerOther
Max output tokens256,000

Use with MegaBrain

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://getmegabrain.com/api/gateway/v1',
  apiKey: process.env.MEGABRAIN_API_KEY,
})

const response = await client.chat.completions.create({
  model: 'stepfun/step-3.7-flash',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use StepFun: Step 3.7 Flash?

Get an API key and start making requests in minutes.

Get an API key