Step 3.5 Flash
A Chinese AI lab's fast assistant model that anyone can free to download and use, offered through a hosting service for developers.
This came out before trckr began following OpenRouter, so it was added on Nov 6 without an alert. Its release date comes from models.dev.
Key facts
- Released
- Jan 29, 2026
- What it does
- Text and chat: Writes, answers questions and holds a conversation.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.
View moreView less
- Knowledge cutoff
- January 2025 · the latest events it learned about
Can I use it?
In an app
No app mentioned so far.
For developers
Developers can use it now through an API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet..
Download
Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..
Price and limits
What developers pay to use it through the API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet., per million Tokens: The small chunks of text a model reads and writes, about three-quarters of a word each. Prices and limits are counted in tokens. sent (input) or written back (output), and how much it can take in at once.
- Input
- $0.105
- per million tokensCached: $0.021
- Output
- $0.314
- per million tokens
- Context window: How much a model can keep in mind at once: your question, any files you share and its own replies. Measured in tokens; 1,000 tokens is about 750 words.
- 256K tokens
- about 190,000 words
View moreView less
- Longest answer
- 66K tokens (about 49,000 words)
From the lab's own listing on models.dev and OpenRouter, checked .
Compare Step 3.5 Flash with
The details
StepFun describes this as its most capable Open source: Strictly, the model's files, code and training recipe are all public and free to reuse. Often used loosely to mean "free to download". foundation model, a sparse Mixture of experts (MoE): A design that splits a big model into many "expert" parts and uses only a few for each word. It gives big-model quality at closer to small-model speed. design with 200 billion parameters: Needs a server with several high-end chips (GPUs). Parameters are the numbers a model learns: a rough measure of its size. that activates 11B per Tokens: The small chunks of text a model reads and writes, about three-quarters of a word each. Prices and limits are counted in tokens.. It is listed on OpenRouter: A service that gives developers one place to use hundreds of models from many labs. New models often appear there early, sometimes anonymously. for developers.
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
stepfun/step-3.5-flashTimeline
/OpenRouterFirst signal
Get alerts like this the moment they happen.
From StepFun and every other major lab.