models/stepfun/step-3-5-flash
S
stepfun·active

StepFun: Step 3.5 Flash

stepfun's mid-tier model. Context window: 262K tokens.

Overall score
4.23
/5.00 · ranked #48
Input
$0.090
per 1M tokens
Output
$0.300
per 1M tokens
Context
262K
tokens
Blended
$0.247
3:1 out:in ratio

Price drops, new benchmarks, model updates. Stay current on StepFun: Step 3.5 Flash.

One email per change. Unsubscribe anytime.

modelpicker.aipowered by live benchmark data

Scores by test

Methodology →
Structured Output
5.0
Strategic Analysis
5.0
Constrained Rewriting
3.0
Creative Problem Solving
4.0
Tool Calling
4.0
Faithfulness
5.0
Classification
4.0
Long Context
5.0
Safety Calibration
2.0
Persona Consistency
5.0
Agentic Planning
4.0
Multilingual
5.0
Tabular Data
4.0

What you need to know

Step 3.5 Flash is optimized for high-precision technical tasks, specifically excelling in structured output, strategic analysis, and faithfulness. With a 262K context window and a perfect 5/5 internal score for long-context processing, this model is designed for reliability when extracting data or analyzing large documents without losing coherence.

The pricing is aggressive, with a blended cost of $0.247/MTok, making it a low-cost option for high-volume production environments. This creates a strong value proposition for developers who need a model that maintains persona consistency and multilingual accuracy without the cost overhead of larger frontier models.

The model's primary limitation is safety calibration, scoring 2/5, which suggests a higher risk of generating unfiltered or non-compliant responses. It also shows moderate weakness in constrained rewriting, indicating it may struggle with strict character counts or rigid formatting constraints during text transformation.

Use this model for complex data extraction, multilingual strategic analysis, and long-context RAG pipelines where cost-efficiency is a priority. Skip this model if your application requires strict safety guardrails or precise, constrained rewriting tasks.

Strengths — Top 3

Structured Output5.0/5.0
Strategic Analysis5.0/5.0
Faithfulness5.0/5.0

Relative weaknesses — Bottom 3

Safety Calibration2.0/5.0
Constrained Rewriting3.0/5.0
Creative Problem Solving4.0/5.0

Similar models

GGemma 4 26B A4B $0.2634.23MMiniMax: MiniMax M2.7$0.9704.23NNVIDIA: Nemotron 3 Ultra$2.004.38OGPT-5.1$7.814.23