modelhub.help

Step 3.7 Flash

StepFun

256K context · — params · —

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...

Cheapest blended: ¥0.4375 / 1M tokens on StepFunGet custom quote

Reachability & verification

Live reachability

Probing…

Target (StepFun): https://api.stepfun.com/v1

Live reachability probe

Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.

Pricing across providers

1

Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.

ProviderInput /1MOutput /1MBlendedCtxp50 latencyAPIVerified
StepFunstep-3.7-flash¥0.2¥1.15¥0.4375256K— OAI91d ago

Works with

CursorClineAiderContinueOpenCodeOpen WebUI

Any OpenAI-compatible client works — point the base URL at the provider endpoint.

Capabilities

Code samplesExample usingStepFun— the cheapest hosting for this model as of last verification. Swapbase_urlandmodelto use a different provider from the matrix above.PythoncURLNode.jsCopyfrom openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.stepfun.com/v1", ) response = client.chat.completions.create( model="step-3.7-flash", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)

Code samples

Python
from openai import OpenAI

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

resp = client.chat.completions.create(
    model="step-3.7-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
cURL
curl https://api.stepfun.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "step-3.7-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.stepfun.com/v1",
  apiKey: "YOUR_API_KEY",
});

const resp = await client.chat.completions.create({
  model: "step-3.7-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Technical specs

Context

256K

Max output

256K

Parameters

—

Release

—

Training cutoff

—

License

—

Similar models

Step 3.5 Flash

StepFun · 262K ctx · Open weight

Step 3.7 Flash

StepFun · 128K ctx

Frequently asked questions

How much does Step 3.7 Flash cost?

The cheapest tracked blended price is ¥0.4375 per 1M tokens on StepFun. See the pricing matrix above for input/output splits per provider.

Can I use Step 3.7 Flash from outside China?

Availability depends on the hosting provider. Use our Path Planner on the StepFun page to map a verified official-vs-brokered access path, including payment and KYC constraints.

Is Step 3.7 Flash open source?

No — Step 3.7 Flash is a proprietary hosted model, available only through APIs.

Is Step 3.7 Flash OpenAI-compatible?

Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.

What is the maximum context window?

Step 3.7 Flash supports up to 256K tokens of context with a maximum output of 256K tokens.

Need verified access to Step 3.7 Flash?

We broker vetted intros to StepFun — payment, KYC and endpoint verification handled.

Request a brokerage intro