Models / stepfun

Step 5 Preview

by stepfun · stepfun/step-5-preview

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...

reasoningtool-usevisionreleased 2026-10-08

JSON Route to this model

Legal score · raw

not yet benchmarked

Context

1.05M

max output 64K

Input

$1.25

per 1M tokens

Output

$3.38

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

$0.13

10x cheaper than uncached

Uncached input

$1.25

per 1M tokens

Capabilities

Modalities

in textimagevideo

out text

Request parameters it accepts

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_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.