Step 3.5 Flash
VerifiedFast LLM built for 256k-token text contexts.
About Step 3.5 Flash
Step 3.5 Flash is engineered as a proprietary LLM with an emphasis on speed and scale. Its 262144-token context window enables processing of lengthy documents or extended dialogues without truncation. The closed weights allow Stepfun to maintain performance optimizations and controlled deployment.
Typical usage includes document summarization, long-context chat systems, and content generation tasks. Developers access the model through APIs where rapid responses on large inputs are required. Its text-only modality keeps the focus on language understanding and generation at extended lengths.
Capabilities
How Step 3.5 Flash compares
Step 3.5 Flash (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Step 3.5 Flash ranks #15 of 72
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long Document Analysis
Step 3.5 Flash excels at processing and extracting insights from extensive documents due to its 262144-token context window and document analysis capabilities.
Code Generation Projects
The model supports efficient code generation and instruction following, making it suitable for developers building or refactoring software components.
Content Summarization Tasks
It performs well on text generation and summarization of lengthy inputs, combining long-context reasoning with question answering for accurate overviews.
Strengths & limitations
Strengths
- +Very large context window for extended inputs
- +Efficient inference as a Flash variant
- +Strong performance on text-only tasks
- +Suitable for large-scale document processing
Limitations
- –Text modality only with no vision or audio support
- –Lacks specialized multimodal capabilities
- –Performance may vary on highly specialized domains
Cost calculator
Estimate what Step 3.5 Flash would cost for your usage.
Based on Step 3.5 Flash's $0.09/1M input · $0.30/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "stepfun/step-3.5-flash",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: stepfun/step-3.5-flash
Editor's verdict
Step 3.5 Flash is Stepfun's proprietary language models with a 262K-token context window.
At $0.30 per 1M output tokens, it is very cost-efficient for its class.
It is available through Stepfun's API and aggregators like OpenRouter.
Best suited to very large context window for extended inputs and efficient inference as a flash variant.
Frequently asked questions
The model provides a context window of 262144 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Step models
Sibling versions in the Step family from Stepfun.
Similar models
Other language models worth comparing.