Skip to content
LLMs
StepFun logo

StepFun: Step 3.7 Flash

by StepFun

StepFun: Step 3.7 Flash is a large language model from StepFun. It costs $0.200 per million input tokens and $1.15 per million output tokens. Its context window is 262K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weightsimage inputvideo input
Input / 1M tokens
$0.200
Output / 1M tokens
$1.15
Cached input / 1M
$0.040

On repeated prefixes

Context window
262K

tokens

Who serves it cheapest

3 hosts serve Step 3.7 Flash. Same weights, same API - the price difference is pure margin and routing.

Providers serving StepFun: Step 3.7 Flash, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
DeepInfraCheapest$0.160$0.920262K-100.0%
Novitafp8$0.200$1.15262K-99.3%
StepFunfp8$0.200$1.15256K-99.4%

The spread between DeepInfra and StepFun is 1.3× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Coding index
39.6

About 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...

Specifications

StepFun: Step 3.7 Flash specifications
Model IDstepfun/step-3.7-flash
ProviderStepFun
Context window262K tokens
Max output230K tokens
Input modalitiestext, image, video
Output modalitiestext
Knowledge cutoff-
Open weightsYes - stepfun-ai/Step-3.7-Flash
ReleasedMay 28, 2026

Cheaper alternatives

Models that cost less than Step 3.7 Flash while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does StepFun: Step 3.7 Flash cost?

$0.200 per million input tokens and $1.15 per million output tokens. Cached input reads cost $0.040 per million tokens.

What is the context window of StepFun: Step 3.7 Flash?

262K tokens, with up to 230K tokens of output per request.

Which provider serves StepFun: Step 3.7 Flash cheapest?

DeepInfra at $0.160 per million input tokens - 1.3× cheaper than StepFun, the most expensive of the 3 hosts serving it.