WLRouter
Models/step-3.7-flash
Model Code
stepfun/step-3.7-flash
Try now

Model overview

Text generationVisionAgentCodingSearch

Step 3.7 Flash is StepFun's efficient production Flash model for agents, coding, search, and multimodal workflows. Alibaba Cloud Bailian lists text and image input, text output, tool calling, structured output, web search, context cache, and mixed thinking mode for this model.

Company: StepFunProvider: Alibaba Cloud

Model capabilities

Input modalityT
Output modalityT
Model experience✓
Function calling✓
Structured output✓
Web search✓
Prefix completion✓
Context cache✓
Batch inference✓
Fine-tuning✓

Model pricing

Input$0.19/1M tokens
Input (cache hit)$0.04/1M tokens
Output$1.13/1M tokens

Rate limits and context

Maximum input length256K
Context length256K
Maximum output length256K
RPM500
TPM20,000,000

API reference

EndpointPOST /v1/chat/completions
SDKOpenAI-compatible

API code examples

Get API Key
from openai import OpenAI

client = OpenAI(
    api_key="$WLROUTER_API_KEY",
    base_url="https://api.wlrouter.com/v1"
)

response = client.chat.completions.create(
    model="stepfun/step-3.7-flash",
    messages=[
        {"role": "user", "content": "Reply with one short sentence."}
    ],
    max_tokens=32,
    extra_body={"enable_thinking": True}
)

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