Hormouz AIHormouzSign in

StepFun: Step 3.5 Flash: AI model

Step 3.5 Flash is StepFun's most capable open-source foundation model. A Mixture-of-Experts reasoning model that activates just 11B of its 196B parameters, with a 262K-token context window. Reachable from inside Iran through Hormouz.

Context window:
262,144 tokens
Input:
$0.1/1M tokens
Output:
$0.3/1M tokens
Type:
text
  • Tools
  • Streaming
  • Long context

Thinking levels: Always thinks

Step 3.5 Flash is StepFun's most capable open-source foundation model. It is built on a sparse Mixture-of-Experts (MoE) architecture, activating only 11B of its 196B parameters per token.

It is a reasoning model that stays remarkably speed-efficient even at long contexts. Its 262K-token context window and tool-calling support make it a fit for multi-step reasoning tasks and agentic workflows. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.

Pricing is usage-based: $0.1/M in · $0.3/M out. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepfun/step-3.5-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorStepFun
TypeText
Context window262,144 tokens
Pricing$0.10/M in · $0.30/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
82.6%
HLE
Humanity's Last Exam
24.5%
IFBench
Instruction-following
66.5%
AA-LCR
Long-context reasoning
63%
CritPt
Research-level physics reasoning
2.3%
AA Omniscience
Broad factual knowledge accuracy
24.6%
Non-Hallucination
Rate of avoiding fabricated answers
8.7%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
32.6%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
87.4%

Source: Artificial Analysis

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepfun/step-3.5-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="stepfun/step-3.5-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "stepfun/step-3.5-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the StepFun: Step 3.5 Flash API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches StepFun: Step 3.5 Flash and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Step 3.5 Flash cost?
Billing is usage-based: $0.1/M in · $0.3/M out. There is no fixed monthly fee. You pay only for what you use.
How do I use Step 3.5 Flash from inside Iran?
Create a Hormouz account and generate an API key. Hormouz gives you a stable route to the model from inside Iran, with no foreign credit card or circumvention tooling needed.
Is Step 3.5 Flash OpenAI-compatible?
Yes. Hormouz serves an OpenAI-compatible API. Point your base URL at Hormouz and swap in a Hormouz key; your existing SDKs and code work without a rewrite.
What is Step 3.5 Flash's architecture?
It is a sparse Mixture-of-Experts model that activates 11B of its 196B parameters per token, delivering both quality and speed.
What is Step 3.5 Flash good for?
Multi-step reasoning tasks, coding and agentic workflows that need high speed even at long contexts.
How large is Step 3.5 Flash's context window?
The context window is up to 262K tokens, and the model supports tool calling.

Updated 2026-10-13