All AI models · LLM benchmarks · Methodology

StepFun

Step 3.5 Flash 2603

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Model facts

Context window
256K tokens
Maximum output
256K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
$0.3 per 1M tokens
Open weights
yes
Providers
6

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default26.5not measurednot measurednot measured

Observed price history

  • 2026-08-24: $0.1 input / $0.3 output per 1M tokens

API providers

  • EmpirioLabs AI — model id step-3-5-flash-2603; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • NanoGPT — model id stepfun-ai/step-3.5-flash-2603; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • StepFun (China) — model id step-3.5-flash-2603; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • StepFun (Global) — model id step-3.5-flash-2603; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • StepFun Step Plan (China) — model id step-3.5-flash-2603; not published input / not published output per 1M tokens; provider documentation
  • StepFun Step Plan (Global) — model id step-3.5-flash-2603; not published input / not published output per 1M tokens; provider documentation