StepFun: Step 3.7 Flash

stepfun/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...

Prompt $/1M

$0.200

Completion $/1M

$1.150

Context

256,000 tok

Best provider

400 tok/s · Artificial Analysis

Specs

Model id: stepfun/step-3.7-flash
Display name: StepFun: Step 3.7 Flash
Modality: text+image+video->text
Tokenizer: Other
Instruct type: —
Context length: 256,000
Max completion: 256,000
Prompt $/1M: $0.200
Completion $/1M: $1.150
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionyes
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Artificial Analysis	400	730 ms	—
DeepInfrafastest	150	411 ms	574 ms
Novita	87	5,312 ms	7,523 ms
Ambient	46	403 ms	493 ms
StepFun	38	5,646 ms	6,998 ms