Hugging Face

Hugging Face: Step 3.7 Flash (Hugging Face)

stable

Step 3.7 Flash (Hugging Face) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

stepfun-ai__Step-3.7-Flashstepfun-ai/Step-3.7-Flashreleased May 29, 2026
ProviderQuick start
Context
262.1K
tokens
Max output
256K
tokens
Input
$0.20
per 1M
Output
$1.15
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
NVIDIA NIM
NVIDIA NIM
256K--
Hugging Face
Hugging Face
262.1K$0.20$1.15
OpenRouter
OpenRouter
262.1K$0.20$1.15

Pricing

ItemPriceUnit
Input$0.20per 1M tokens
Output$1.15per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
stepfun-ai__Step-3.7-Flash
Family
stepfun-ai/Step-3.7-Flash
Status
stable
Knowledge
Mar 1, 2026
Released
May 29, 2026
Gateway Config
API
2024-01-01
Auth
HUGGINGFACE_API_KEY
Discovery
dynamic
Provider type
meta

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@huggingface/stepfun-ai__Step-3.7-Flash",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://router.huggingface.co/v1
Chat completions
https://router.huggingface.co/v1/chat/completions
Model
stepfun-ai__Step-3.7-Flash
Auth env
HUGGINGFACE_API_KEY

Step 3.7 Flash (Hugging Face) FAQ

How much does the Step 3.7 Flash (Hugging Face) API cost?

Through Hugging Face, Step 3.7 Flash (Hugging Face) costs $0.20 per 1M input tokens and $1.15 per 1M output tokens.

What is the context window of Step 3.7 Flash (Hugging Face)?

Step 3.7 Flash (Hugging Face) accepts up to 262.1K tokens of context and returns up to 256K output tokens on Hugging Face.

Which providers offer Step 3.7 Flash (Hugging Face)?

Step 3.7 Flash (Hugging Face) is available from NVIDIA NIM, Hugging Face and OpenRouter. Everstack can route between them with automatic fallback when one is unavailable.

What can Step 3.7 Flash (Hugging Face) do?

Step 3.7 Flash (Hugging Face) supports chat, function calling, image input and reasoning. It accepts text, image and video input.

How do I call Step 3.7 Flash (Hugging Face) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @huggingface/stepfun-ai__Step-3.7-Flash. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.