StepFun model product
Step 3.5 Flash
5-Flash is StepFun's fast, cost-effective text model optimized for quick inference.
Updated Aug 12, 2026. Default version: Step-3.5-Flash
LLMBoard score60.4Step-3.5-Flash
Coverage40%7 benchmark families
Context window256KTokens
Official input price$0.10StepFun (Global) API
Step 3.5 Flash Specifications
Technical details for the model's default version.
- Version
- Step-3.5-Flash
- Released
- Feb 2, 2026
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- 196B
- Context window
- 256K
- Max output
- 256K
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Step 3.5 Flash Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Step 3.5 Flash Benchmark Results
Benchmark scores for Step-3.5-Flash.
| Tau-bench | 88.2% | 01 | 6 | 100.0% | C | |
| LiveCodeBench v6 | 86.4% | 08 | 53 | 86.5% | C | |
| IMO-AnswerBench | 85.4% | 09 | 19 | 55.6% | C | |
| AIME 2025 | 97.3% | 14 | 114 | 88.5% | C | |
| BrowseComp | 69.0% | 30 | 58 | 49.1% | C | |
| Terminal-Bench 2.0 | 51.0% | 34 | 49 | 31.3% | C | |
| SWE-Bench Verified | 74.4% | 39 | 105 | 63.5% | C |
Step 3.5 Flash Arena Results
Preference and agent-evaluation results for the default version.
| text factuality | overall | 113 | 1417.5 | 57,180 | N/A | |
| text | overall | 128 | 1403.8 | 57,542 | N/A | |
| text style control | overall | 146 | 1394.6 | 57,542 | N/A |
Step 3.5 Flash Runtime Performance
Provider-specific output speed and catalog latency for Step-3.5-Flash. Runtime does not affect the capability score.
| StepFun | 122.942 tok/s | 1.192 s | 65.5K | 8.2K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Step 3.5 Flash Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.10 input, $0.30 output per 1M
- Official provider
- StepFun (Global)
- Lowest third-party
- From $0.09 input, $0.30 output per 1M via Vercel AI Gateway
- Tracked offerings
- 13
| Nvidia | stepfun-ai/step-3.5-flash | global | N/A | N/A | 256K | |
| Vercel AI Gateway | stepfun/step-3.5-flash | global | $0.09 | $0.30 | 262.1K | |
| NanoGPT | stepfun-ai/step-3.5-flash | global | $0.10 | $0.30 | 256K | |
| ZenMux | stepfun/step-3.5-flash | global | $0.10 | $0.30 | 256K | |
| EmpirioLabs AI | step-3-5-flash | global | $0.10 | $0.30 | 256K | |
| Kilo Gateway | stepfun/step-3.5-flash | global | $0.10 | $0.30 | 262.1K | |
| OpenRouter | stepfun/step-3.5-flash | global | $0.10 | $0.30 | 262.1K | |
| Hugging Face | stepfun-ai/Step-3.5-Flash | global | $0.10 | $0.30 | 262.1K | |
| StepFun (Global) | step-3.5-flash | global | $0.10 | $0.30 | 256K | |
| StepFun (China) | step-3.5-flash | global | $0.10 | $0.30 | 256K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Step 3.5 Flash Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Step-3.5-Flash | 60.4 | 196B | 256K | 256K | Yes | Apache 2.0 |
What is Step 3.5 Flash?
Key information about Step 3.5 Flash and its available data.
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.
Data as of 2026-08-11.
Step 3.5 Flash vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Step 3.5 Flash
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ST
Step3 VL 10B
StepFun
OP
GPT-5.4-mini
OpenAI
AC
Qwen3.6 27B
Alibaba Cloud / Qwen Team
GO
Google
Gemma 4 31B
ME
LongCat Flash Thinking
Meituan
MA
Kimi K2 Thinking
Moonshot AI
FAQ
Common questions about Step 3.5 Flash.
When was Step 3.5 Flash released?
Step 3.5 Flash's default version was released on Feb 2, 2026.
How much does Step 3.5 Flash cost?
Step 3.5 Flash's official API price is $0.10 per million input tokens and $0.30 per million output tokens via StepFun (Global). The lowest tracked third-party offer starts at $0.09 input and $0.30 output via Vercel AI Gateway.
Who created Step 3.5 Flash?
Step 3.5 Flash was created by StepFun.
What is the context window for Step 3.5 Flash?
The default version has a 256K token context window.
Is Step 3.5 Flash open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Step 3.5 Flash?
13 provider offerings are linked to the default version.
What models should I compare Step 3.5 Flash with?
Nearby ranked alternatives include LongCat Flash Thinking, Qwen3.6 27B, GPT-5.4-mini.