Stepfun

Step 3.7 Flash

Chat
Not available
Get started

Most cost-effective multimodal model. 198B total, ~11B active (sparse MoE). Supports vision + video input with tunable reasoning tiers.

Context
256Ktokens
Max output
256Ktokens
Latency
~10ms
Released
2026-02

Pricing

$ / 1M tokens
Input
$0.20/M
Output
$1.15/M
Cache Read
$0.04/M
Cache Write
$0.20/M

Capabilities

3 listed
  • Chat
  • Tool Use
  • Coding

Code examples

POST /v1/chat/completions
python
from openai import OpenAI

client = OpenAI(
    api_key="your_api_key",
    base_url="https://api.modelstack.cc/v1",
)

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

Related models

Frequently asked questions

How is Step 3.7 Flash billed on ModelStack?expand_more
ModelStack bills based on actual request usage. Input, output, cache, and any other applicable rates follow the live pricing table on this page. Final request costs are available in the console.
What are the context window and maximum output for Step 3.7 Flash?expand_more
Step 3.7 Flash has a 256K context window and supports up to 256K of output.
How can I call Step 3.7 Flash through ModelStack?expand_more
Use the model ID `step-3.7-flash` with any OpenAI-compatible SDK pointed at the ModelStack API — see the code examples above for Python, Node.js, and cURL.
Which capabilities does Step 3.7 Flash support?expand_more
Step 3.7 Flash supports: Chat, Tool Use, Coding.