---
id: "stepfun/step-3.5-flash"
also: ["stepfun/step-3.5-flash", "stepfun-ai/Step-3.5-Flash", "hf/stepfun-ai/Step-3.5-Flash", "vercel/stepfun/step-3.5-flash"]
cheapest_list_usd_per_m: "0.09 in, 0.3 out, at deepinfra on vercel"
cheapest_effective_usd_per_m: "0.09 in, 0.3 out, at deepinfra on vercel"
context: 262144
max_output: 65536
input: ["text"]
output: ["text"]
released: "2026-01-29"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 4
gateways: "hf (2), openrouter (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# StepFun: Step 3.5 Flash

Step 3.5 Flash is an open-source reasoning model by StepFun with 196B total parameters (11B active) using Mixture of Experts. It features a 256K context window, deep reasoning, tool calling, and agentic capabilities, achieving 97.3 on AIME 2025 and 74.4% on SWE-bench Verified.