Models / stepfun
Step 3.7 Flash
by stepfun ·
stepfun/step-3.7-flashStep 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...
reasoningtool-usevisionreleased 2026-05-28
Legal score · raw
-
not yet benchmarked
Context
262K
max output 230K
Input
$0.25
per 1M tokens
Output
$1.44
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.05
5.0x cheaper than uncached
Uncached input
$0.25
per 1M tokens
Capabilities
Modalities
in textimagevideo
out text
Request parameters it accepts
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.