Quickstart

This guide provides a common set of API examples. Select a model ID from the table, then use the tabs below to switch between text chat, image understanding, and video understanding.

​

Choose a model ID

Model	Model ID	Input capabilities
Step 5 Preview	step-5-preview	Text, images, and video
Step 3.7 Flash	step-3.7-flash	Text, images, and video
Step 3.5 Flash	step-3.5-flash	Text only

Replace YOUR_MODEL_ID in the examples below with one of the model IDs in the table, and replace YOUR_STEP_API_KEY with your API key.

​

Get an API key

Sign in to the StepFun Open Platform and create and copy an API key on the Interface Keys page.

​

Set up your environment

​

Install the Python dependency

The Python examples use the OpenAI SDK:

macOS / Linux

python3 -m pip install --upgrade "openai>=1.0"

Windows

py -m pip install --upgrade "openai>=1.0"

​

Send a request

Text chat

This example works with all three models. Replace YOUR_MODEL_ID with the model you want to call.

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_STEP_API_KEY",
    base_url="https://api.stepfun.ai/v1",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[
        {"role": "user", "content": "Hello, please introduce yourself in one sentence."}
    ],
)

print(response.choices[0].message.content)

cURL

curl https://api.stepfun.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_STEP_API_KEY" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {
        "role": "user",
        "content": "Hello, please introduce yourself in one sentence."
      }
    ]
  }'

Image understanding

Step 5 Preview and Step 3.7 Flash support image input. Step 3.5 Flash does not support image input; use a model that supports images instead.

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_STEP_API_KEY",
    base_url="https://api.stepfun.ai/v1",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Extract the key information from this image and summarize the main conclusions."},
            {
                "type": "image_url",
                # Replace this placeholder with the URL of your own accessible image.
                "image_url": {"url": "https://example.com/image.jpg"},
            },
        ],
    }],
)

print(response.choices[0].message.content)

cURL

# Replace this placeholder with the URL of your own accessible image.
curl https://api.stepfun.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_STEP_API_KEY" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Extract the key information from this image and summarize the main conclusions."},
        {
          "type": "image_url",
          "image_url": {"url": "https://example.com/image.jpg"}
        }
      ]
    }]
  }'

Video understanding

Step 5 Preview and Step 3.7 Flash support video input through video_url. Step 3.5 Flash does not support video input; use a model that supports video instead.

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_STEP_API_KEY",
    base_url="https://api.stepfun.ai/v1",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Summarize the main content of this video in chronological order."},
            {
                "type": "video_url",
                # Replace this placeholder with the URL of your own accessible video.
                "video_url": {"url": "https://example.com/video.mp4"},
            },
        ],
    }],
)

print(response.choices[0].message.content)

cURL

# Replace this placeholder with the URL of your own accessible video.
curl https://api.stepfun.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_STEP_API_KEY" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Summarize the main content of this video in chronological order."},
        {
          "type": "video_url",
          "video_url": {"url": "https://example.com/video.mp4"}
        }
      ]
    }]
  }'

​

Read the response

For a non-streaming request, generated content is available in choices[0].message.content:

{
  "model": "YOUR_MODEL_ID",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "The model's response"
      },
      "finish_reason": "stop"
    }
  ]
}

The full response also includes the request ID, token usage, and other fields. See the Chat Completions API for details.

If a request fails, use the returned error information and refer to the error codes documentation.

​

Explore further

Model capability overview

Compare the positioning and capabilities of Step 5 Preview, Step 3.7 Flash, and Step 3.5 Flash.

Image understanding best practices

Learn about image formats, input methods, and parameter recommendations.

Video understanding best practices

Learn about video input methods, limits, and common issues.

API reference

See the complete request parameters, response fields, and usage information.