Step 3.7 Flash API

CN StepFun | リリース 2026-10

Step 3.7 Flash is StepFun’s flagship multimodal reasoning model on a 198B-total / 11B-active sparse MoE architecture, with native image input and fast responses. Strong on reasoning-heavy multimodal tasks at a price well below Western frontier models.

cap.vision推論高速

料金 (公式、1Mトークンあたり)

入力

$0.20/M

出力

$1.20/M

仕様

コンテキストウィンドウ256K トークン入力モダリティテキストストリーミングはい APIOpenAI互換

Step 3.7 Flashの使い方

OpenAIの直接代替。base_urlとモデルのみ変更。

# Python - pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://meshtok.com/v1",
    api_key="sk-your-MeshTok-key",
)

resp = client.chat.completions.create(
    model="stepfun/step-3.7-flash",
    messages=[{"role":"user","content":"Hello!"}],
)
print(resp.choices[0].message.content)

# cURL
curl https://meshtok.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-MeshTok-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"stepfun/step-3.7-flash","messages":[{"role":"user","content":"Hello!"}]}'