Released 57 days after Step 3.5 Flash Β· All StepFun releases
Step 3.7 Flash brings StepFun's Step series down to a high-efficiency footprint, released as open weights in May 2026. The model is a sparse mixture-of-experts design that activates roughly 11 billion of its 198 billion total parameters per token and pairs the language backbone with a compact vision encoder, adding native image input that the earlier 3.5 Flash generation lacked. Selectable reasoning levels let callers trade depth for speed on each request, and the model is tuned for agent frameworks with reliable tool calling, MCP support, and structured output. It suits coding agents, search and retrieval workflows, and screenshot-driven automation that want capable multimodal behavior at small-model inference cost, backed by a 262K context window and outputs up to 256K tokens.
Step 3.7 Flash runs on 1 route through the qynio gateway. Compare residency, zero retention, and training posture at a glance β full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Zero data retention | No | $0.20 | $1.15 |
Step 3.7 Flash runs on a single route through the qynio gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.
Each route hosting Step 3.7 Flash has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go β no action required. No training on customer data. US; wallets; deposit available.
Independent benchmark scores β composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Step 3.7 Flash through the qynio gateway with one API key. Let your coding agent set it up, or call it directly β qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.QYN_API_KEY,baseURL: "https://api.qyn.io/v3/compat",});const completion = await client.chat.completions.create({model: "novita/stepfun/step-3.7-flash",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, crypto rails, pricing, and benchmarks.
