Back to all models

Step 3.7 Flash

StepFun's high-efficiency multimodal MoE model (196B language backbone, ~11B active) with native image and video understanding.

step-3.7-flash
STABLEGet StartedView uptime
262,144 context
Released May 28, 2026
Starting at $0.20/M input tokens
Starting at $1.15/M output tokens
Streaming
Vision
Tools
Reasoning
No ratings yetSign in to rate

Select Provider

All Providers for Step 3.7 Flash

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

DeepInfra
Context: 262.1k
Input
$0.2
/M tokens
Cache Read
$0.04
/M tokens
Output
$1.15
/M tokens
Get Started
NovitaAI
Context: 262.1kQuant: fp8
Input
$0.2
/M tokens
Cache Read
$0.04
/M tokens
Output
$1.15
/M tokens
Get Started

Frequently asked questions

What is Step 3.7 Flash?

StepFun's high-efficiency multimodal MoE model (196B language backbone, ~11B active) with native image and video understanding. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does Step 3.7 Flash cost?

Pricing for Step 3.7 Flash on LLM Gateway starts at $0.20 per million input tokens and $1.15 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of Step 3.7 Flash?

Step 3.7 Flash supports a context window of up to 262,144 tokens on its largest provider deployment.

Which providers serve Step 3.7 Flash?

Step 3.7 Flash is served by DeepInfra, NovitaAI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does Step 3.7 Flash support tool calling and structured outputs?

Step 3.7 Flash supports tool (function) calling, but not JSON output modes.

When was Step 3.7 Flash released?

Step 3.7 Flash was released on May 28, 2026.