EN / 中文
Model prices / StepFun / Step 3.7 Flash

Step 3.7 FlashOpen weights

StepFun · released 2026-05-29

The official API price of Step 3.7 Flash is $0.20175 per 1M input tokens and $1.21052 per 1M output tokens (as of 2026-11-12). Context window: 256K tokens, up to 256K output tokens per request. 21 providers sell it. The lowest is CommandCode: $0.2 input, $1.15 output.

Price by providerUSD per 1M tokens

ProviderInputOutputCachedNotes
StepFun (China)Officialstep-3.7-flash
$0.20175$1.21052$0.04035OfficialOfficial docs
CommandCodeLoweststepfun/Step-3.7-Flash
$0.2$1.15$0.04LowestOfficial docs
EEden AIdeepinfra/stepfun-ai/Step-3.7-Flash
$0.2$1.15$0.04Official docs
EmpirioLabs AIstep-3-7-flash
$0.2$1.15$0.04Official docs
Hugging Facestepfun-ai/Step-3.7-Flash
$0.2$1.15—Official docs
KKilo Gatewaystepfun/step-3.7-flash
$0.2$1.15$0.04Official docs
DevPass (LLM Gateway)step-3.7-flash
$0.2$1.15$0.04Official docs
LLLM Gatewaynovita/step-3.7-flash
$0.2$1.15$0.04Official docs
NNanoGPTstepfun/step-3.7-flash:thinking
$0.2$1.15$0.04Official docs
Novita AIstepfun/step-3.7-flash
$0.2$1.15$0.04Official docs
OpenRouterstepfun/step-3.7-flash
$0.2$1.15$0.04Official docs
RRequestystep-3.7-flash
$0.2$1.15$0.04Official docs
10 more listings
ProviderInputOutputCachedNotes
SStepFun (Global)step-3.7-flash
$0.2$1.15$0.04Official docs
Vercel AI Gatewaystepfun/step-3.7-flash
$0.2$1.15$0.04Official docs
ZenMuxstepfun/step-3.7-flash
$0.2$1.15$0.04Official docs
AIHubMixstep-3.7-flash
$0.22$1.32$0.044Official docs
KKenaristep-3-7-flash
$0.24$1.371429$0.048Official docs
Deep InfraDeprecatedstepfun-ai/Step-3.7-Flash
$0.2$1.15$0.04DeprecatedOfficial docs
KKenariDeprecatedstep-3-7-flash:free
$0$0—DeprecatedOfficial docs
UUnoRouterDeprecatedstep-3.7-flash:free
$0$0—DeprecatedOfficial docs
———Official docs
———Official docs

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

About

Newer StepFun flash model for faster agents, coding, and multimodal prompts

Description from models.dev.

Specs

Type
Text
Context
256K
Max output
256K
Input
Text, Image, Video
Output
Text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Knowledge cutoff
2026-03-01
Open weights
Yes
Released
2026-05-29

Source

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.