Textby 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...

  • By price it is in the cheaper half of the 348 text models GenMagic runs (136th cheapest).
  • It has scores on 12 public benchmarks, listed below with their sources.
  • It was listed on May 28, 2026.

Data last changed Nov 12, 2026 · tracked since Oct 29, 2026 · Every model change

Try Step 3.7 Flash

Generate with Step 3.7 Flash right here. Verify your email to start with free credits.

<$0.01
Try

Specifications

Context window

262K tokens

Max output

230K tokens

Input price

$0.30 / 1M tokens

Output price

$1.73 / 1M tokens

Cached input

$0.06 / 1M tokens

Benchmarks

How Step 3.7 Flash scores on public benchmarks. Each card links to the benchmark explainer and to the original source.

39.6

source date 2026-11-11
Source: openrouter
Design Arena: 3DDesign & Generation

1114 Elo

Source: designarena
Design Arena: CodeDesign & Generation

1176 Elo

Source: designarena
Design Arena: SVGDesign & Generation

1076 Elo

Source: designarena
GPQA DiamondReasoning & Knowledge

76.6%

source date 2026-07-18
Source: openrouter
tau-bench (Airline)Agentic & Tool Use

77.3%

source date 2026-07-18
Source: openrouter

Compare against every model in the full benchmark matrix.

Capabilities

Reasoning

Works through multi-step problems before answering, for harder tasks.

Vision input

Accepts images alongside text, so you can prompt with pictures and screenshots.

Tool use

Can call functions and tools, enabling agentic and structured workflows.

Structured output

Returns validated JSON that conforms to a schema you define.

Use Step 3.7 Flash through the API

The model id is stepfun/step-3.7-flash. Requests bill your GenMagic balance at the price above, and each response reports what it cost.

curl
curl https://genmagic.co/api/v1/chat/completions \
  -H "Authorization: Bearer $GENMAGIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepfun/step-3.7-flash",
    "messages": [{ "role": "user", "content": "Explain vector databases in two sentences." }]
  }'
Python (openai SDK)
from openai import OpenAI

client = OpenAI(base_url="https://genmagic.co/api/v1", api_key="YOUR_GENMAGIC_API_KEY")

resp = client.chat.completions.create(
    model="stepfun/step-3.7-flash",
    messages=[{"role": "user", "content": "Explain vector databases in two sentences."}],
)
print(resp.choices[0].message.content)

From an AI agent, call generate_text with "model": "stepfun/step-3.7-flash" on the GenMagic MCP server. Keys, limits and every endpoint are in the API documentation.

Use Step 3.7 Flash in n8n

  1. In n8n, open the nodes panel, search for GenMagic and install it (a verified community node), then add it to your workflow.
  2. Set Resource to Text and Operation to Generate.
  3. In Model Name or ID, pick StepFun: Step 3.7 Flash, or enter stepfun/step-3.7-flash as an expression.
  4. Connect your GenMagic API key (get one free). Each run is billed at the price above, and the node returns what it cost.

Ready-to-import workflows that already use the node are on GenMagic for n8n.

Similar-priced text models from other providers

Other text models GenMagic runs at a comparable price, on the same balance and API key.

ModelProviderPriceContext
StepFun: Step 3.7 Flash (this model)StepFun$0.30 in / $1.73 out per 1M tokens262K
MiniMax: MiniMax M2.5MiniMax$0.41 in / $1.62 out per 1M tokens200K
Qwen: Qwen3.6 FlashQwen$0.28 in / $1.69 out per 1M tokens1M
Xiaomi: MiMo-V2.6-ProXiaomi$0.65 in / $1.30 out per 1M tokens1.1M
OpenAI: GPT-5.6 Luna ProOpenAI$0.30 in / $1.80 out per 1M tokens1.1M
Thinking Machines: Inkling 2 SmallThinkingmachines$0.45 in / $1.50 out per 1M tokens1M

More from StepFun

All 3 StepFun models

Price and listing history

Every change GenMagic has recorded for Step 3.7 Flash since it began tracking the model on Oct 29, 2026. Prices are GenMagic's, the same the studio and the API charge.

DateChangeBeforeAfter
Nov 1, 2026Price up 36%$0.22 in / $1.26 out per 1M tokens$0.30 in / $1.73 out per 1M tokens

Where these figures come from

  • Price: GenMagic's own price, what the studio and the API charge, recomputed from the provider's price list every few minutes and recorded daily. How pricing works.
  • Specs and description: as StepFun publishes them (model card on Hugging Face), checked daily.
  • Benchmarks: 12 scores from Artificial Analysis and OpenRouter, Design Arena, Epoch AI, re-read daily. Each score above links to its source.
  • Changes: the data on this page last changed on Nov 12, 2026, tracked since Oct 29, 2026. Every model's new listings, price changes and retirements are in the model changes log, and how every figure on GenMagic is sourced is on our sources page.

Generate with Step 3.7 Flash today

One GenMagic plan unlocks Step 3.7 Flash and every other model across text, image, audio, and video.