Skip to main content

Step 3.5 Flash 2603

StepFunOpen WeightApache 2.0 · Commercial OK

Description

Step-3.5-Flash is StepFun's fast, cost-effective text model optimized for quick inference. Built on their Step3 architecture, it offers strong performance across text tasks with low latency and efficient token usage, ideal for production workloads requiring speed and cost efficiency.

Release Date
2026-04-02
Parameters
196.0B
Context Length
256K
Modalities
image, text

Capability Radar

80
general
60
coding
90
reasoning
77
scienceest.
70
agents
80
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

General

Tau-bench88.2%SR

Math

AIME 202597.3%SR
IMO-AnswerBench85.4%SR

Reasoning

LiveCodeBench v686.4%SR
SWE-Bench Verified74.4%SR
BrowseCompOpenAI (2025)69.0%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)51.0%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Math
90
Reasoning
80
General
80
Search
70
Frontend Development
70
Agents
70
Tool Calling
70
Code
60

Pricing

Input Price$0.1 / 1M tokens
Output Price$0.3 / 1M tokens
Blended Price (3:1)$0.175 / 1M tokens
Cache Read Price$0.02092 / 1M tokens

Speed

Tokens/sec154.6
Time to First Token3.32s
Time to Answer16.26s

Provider Price Ranking

Provider Price Ranking

4 providers

Cheapest: StepFunMost Expensive: StepFun (China)
ProviderInputOutput
1StepFunPRIMARY
$0.1
$0.3
2StepFun (Global)
$0.1
$0.3
3EmpirioLabs AI
$0.1
$0.3
4StepFun (China)
$0.10461
$0.31384

Compare pricing across different API providers for this model.

External Sources