StepFun logo

Step 3.5 Flash

stepfun/step-3.5-flash

StepFun flash lane for quick multimodal reasoning and coding assistance

Source-linkedOpen weightsReleased 2026-01-29
Report data
Context window256K
Maximum output256K
Provider offers10
Knowledge cutoff2025-01
Capabilities

What this model supports

ReasoningYes
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsYes
Creator
StepFun
Family
Not documented
Modalities
Text
License
Not documented
Release date
2026-01-29
Model ID
stepfun/step-3.5-flash
Market availability

Provider pricing

Report price →
Providers offering Step 3.5 Flash
ProviderProvider model IDContextInput / 1MOutput / 1MCached / 1MFeaturesAll pricing
Nvidiastepfun-ai/step-3.5-flash256K$0.000$0.000R T ·
View
{
  "input": 0,
  "output": 0
}
Qiniustepfun/step-3.5-flash64K· · ·
View
{}
Vercel AI Gatewaystepfun/step-3.5-flash262.114K$0.090$0.300$0.020R T ·
View
{
  "cache_read": 0.02,
  "input": 0.09,
  "output": 0.3
}
ZenMuxstepfun/step-3.5-flash256K$0.100$0.300· T ·
View
{
  "input": 0.1,
  "output": 0.3
}
StepFun AIstep-3.5-flash256K$0.100$0.300$0.020R T ·
View
{
  "cache_read": 0.02,
  "input": 0.1,
  "output": 0.3
}
StepFunstep-3.5-flash256K$0.100$0.300$0.020R T ·
View
{
  "cache_read": 0.02,
  "input": 0.1,
  "output": 0.3
}
EmpirioLabs AIstep-3-5-flash256K$0.100$0.300$0.020R T ·
View
{
  "cache_read": 0.02,
  "input": 0.1,
  "output": 0.3
}
Kilo Gatewaystepfun/step-3.5-flash256K$0.100$0.300$0.020R T ·
View
{
  "cache_read": 0.02,
  "input": 0.1,
  "output": 0.3
}
OpenRouterstepfun/step-3.5-flash262.144K$0.100$0.300R T ·
View
{
  "input": 0.1,
  "output": 0.3
}
Hugging Facestepfun-ai/Step-3.5-Flash262.144K$0.100$0.300R T ·
View
{
  "input": 0.1,
  "output": 0.3
}
Evidence

Published benchmark results

Artificial Analysis Coding Index vs top 7 models
GPT-5-Codex
38.9
Step 3.5 Flash 2603
34.6
North Mini Code
33.4
Gemini 2.5 Pro
32.0
Step 3.5 Flash
31.6
GLM-4.6
29.5
Qwen3 Max
26.4
SWE-Bench Verified vs top 8 models
Claude Fable 5
95.0
Claude Opus 4.8
88.6
Claude Sonnet 5
85.2
Ornith 1.0 397B
82.4
DeepSeek V4 Pro
80.6
Qwen3.7 Max
80.4
Kimi K2.6
80.2
Step 3.5 Flash
74.4
SciCode vs top 7 models
Fugu
60.1
Fugu Ultra
58.7
Qwen3.7 Max
53.5
Gemini 2.5 Pro
42.8
GPT-5-Codex
40.9
Step 3.5 Flash
40.4
Gemini 2.5 Flash
39.4
Terminal-Bench Hard vs top 7 models
GPT-5-Codex
37.9
Step 3.5 Flash 2603
32.6
Step 3.5 Flash
27.3
Gemini 2.5 Pro
26.5
GLM-4.6
25.0
GLM-4.5
22.0
GLM-4.5-Air
20.5