tokenstat
tokenstat

NVIDIA: Step 3.5 Flash

nvidia/step-3.5-flash · rates as of · Benchmarks · AI plans · Calculator

StepFun flash lane for quick multimodal reasoning and coding assistance

Cheapest input
$0.09
$/MTok · models.dev
Cheapest output
$0.3
$/MTok
Context
262K
tokens
Sources
3
13 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestdeepinfra/stepfun-ai/Step-3.5-FlashEden AI$0.09$0.3$0.02262K
models.devstepfun/step-3.5-flashVercel AI Gateway$0.09$0.3$0.02262K
models.devstep-3-5-flashEmpirioLabs AI$0.1$0.3$0.02256K
models.devstepfun-ai/Step-3.5-FlashHugging Face$0.1$0.3$0262K
models.devstepfun-ai/step-3.5-flashNanoGPT$0.1$0.3$0.05262K
models.devstepfun-ai/Step-3.5-FlashSiliconFlow (China)$0.1$0.3$0262K
models.devstepfun-ai/Step-3.5-FlashSiliconFlow$0.1$0.3$0262K
models.devstep-3.5-flashStepFun (Global)$0.1$0.3$0.02256K
models.devstepfun/step-3.5-flashKilo Gateway$0.1$0.3$0262K
OpenRouterstepfun/step-3.5-flashOpenRouter$0.1$0.3$0.01262K
models.devstep-3.5-flashStepFun (China)$0.1$0.3$0.02256K
models.devstepfun/step-3.5-flashZenMux$0.1$0.3$0256K
LiteLLMstep-3.5-flashN/A$0.1$0.3$0.01N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2025-01Released: 2026-01-29Family: step

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.