Back to Models

Step 3.5 Flash 2603

![StepFun](https://artificialanalysis.ai/img/logos/stepfun_small.svg)StepFun
38/ 57

Intelligence Score

Intelligence

38

#52 of 212 (top 25%)

Speed

150 tok/s

#44 of 141

Price

Free

per M tokens

Context Window

256K

tokens

Latency: 1ms (#41)

Score Breakdown

Quality Score63%
Speed Score19%
Cost Score100%

Similar Models

o3

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI

38intelligence

GPT-5.4 nano

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI

38intelligence

GPT-5.4 mini (medium)

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI

38intelligence

DeepSeek V4 Pro

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek

39intelligence

Mistral Medium 3.5

![Mistral](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fmistral_small.png&w=32&q=75)Mistral

39intelligence

Use This Model

Claude Code

claude --model step-3-5-flash

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "step-3-5-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("step-3-5-flash"),
  prompt: "Hello",
});
Back to Models