Stepfun
Stepfun
VideoOpen Weights (Open) Verified Architecture & SpecsFree ($0 API Tokens)

Step 3.7 Flash

Step 3.7 Flash is a video model from Stepfun with Open Weights parameters, supporting a 256,000-token context window, with text, image, video modalities. Open-weight for self-hosted or compatible deployments.

Technical Architecture & Execution Specifications
Architecture Overview

Step 3.7 Flash

Step 3.7 Flash is a video model from Stepfun with Open Weights parameters, supporting a 256,000-token context window, with text, image, video modalities. Open-weight for self-hosted or compatible deployments.

Supported Modalities
textimagevideo

Hardware & Execution ParametersVideo

Total Parameter CountOpen Weights
Active Parameters (MoE)Dense Architecture
Context Window Capacity256,000 tokens
Model Weights FootprintCloud Hosted API
Distribution LicenseOpen Weights (Open)
Standard API Pricing (1M Tokens)Free / Self-Hosted
Model Heritage & Evolutionary Lineage

Genealogical Graph & Evolutionary Provenance

Tracing foundational base architecture ancestry, architectural successors, scale siblings, and reasoning distillation derivatives.

Independent Foundation Checkpoint

Step 3.7 Flash operates as an autonomous foundation model architecture without direct precursor derivatives in this catalog.

Root Architecture Node
AI Model Architecture & Intelligence

Architecture Engineering & Capability Deep-Dive

An objective architectural evaluation of Step 3.7 Flash by Stepfun, analyzing underlying compute dynamics, memory constraints, and deployment economics.

Topology & Attention Mechanics

A robust autoregressive transformer utilizing standard attention patterns for predictable and coherent token generation.

Architecture Type:Advanced Transformer

Evaluation Profile & Reasoning

Exhibits frontier-tier behavior in reasoning and coding.

Domain Specialty:Video

LLM Hardware Sizing & Serving

For open deployments via vLLM/SGLang, quantization (INT4/AWQ) is heavily recommended to fit dense memory constraints, or multi-GPU pipeline parallelism for full FP16.

KV Cache Mgmt: PagedAttention / FlashAttention-3
Hosting Type:Open Weights (Open)

Inference Economics & Workflows

Well-suited for enterprise pipelines where capability is balanced against per-million token costs.

Enterprise Fit:Production Ready
Production Trade-Offs & Capability Balance

Architectural Strengths vs. Considerations

An objective balance sheet analyzing the operational advantages and production constraints of deploying Step 3.7 Flash.

Key Architectural Strengths

  • Massive 256,000-token context allows full-repository and book-length ingestion.
  • Demonstrated SWE-Bench Pro evaluation score of 56.3% in verified benchmarks.

Operational Considerations

  • 128k+ token prefill stages become heavily compute-bound and balloon KV cache without PagedAttention chunking.
LLM Hardware Sizing & Runtime Compatibility

Inference Runtimes & Hardware Sizing

Deployment targets, inference engines, and memory requirements for Step 3.7 Flash.

Recommended Hardware Profile:
1x RTX 4070 / 4080 (16GB) or Mac M-Series (16GB Unified)
Consumer GPU (< 16 GB VRAM)
Est. 0.0 GB (FP16) / 0.0 GB (INT4)
Production Serving Recipes
vLLM Production
python3 -m vllm.entrypoints.openai.api_server --model Step 3.7 Flash --tensor-parallel-size 1 --gpu-memory-utilization 0.95 --max-model-len 4096 --enable-chunked-prefill
Ollama / llama.cpp
ollama run step 3.7 flash
SGLang Structured
python3 -m sglang.launch_server --model-path Step 3.7 Flash --tp 1 --trust-remote-code
TGI Serving
text-generation-launcher --model-id Step 3.7 Flash --num-shard 1 --max-batch-prefill-tokens 32000
Supported Inference Engines
vLLM

High-throughput PagedAttention server

Supported
Ollama

One-click CLI & local desktop serving

Supported
SGLang

Fast multi-turn structured decoding

Supported
TGI

Text Generation Inference

Supported
Llama.cpp

GGUF CPU/Apple Silicon execution

Supported
Precision & Quantization Formats
BF16 / FP16Full Precision

~0.0 GB VRAM required

FP8 (E4M3)Native FP8

~0.0 GB VRAM (Hopper speedup)

AWQ / GPTQ (4-bit)Activation-Aware

~0.0 GB VRAM

GGUF (Q4_K_M)Quantized Binary

CPU RAM / Apple Silicon optimized

LLM Benchmark Database & Performance Metrics

11 Tested

Standardized evaluation results across reasoning, agentic coding, computer use, and alignment.

Flagship Headline MetricsIndustry SOTA Standard
Coding & Software

SWE-Bench Pro

56.3%resolve rate
0%100%
Coding & Software

SWE-Bench Verified

76.5%resolved
0%100%
SWE-Bench Pro
resolve rate
56.3%
SWE-Bench Verified
resolved
76.5%
Terminal-Bench
success rate
59.6%
Humanity's Last Exam
accuracy
47.2%
BrowseComp
accuracy
75.8%
Toolathlon
success rate
49.5%
GDPval
wins or ties
45.8%
ClawEval
pass^3
67.1%
Commercial Rates & Inference Costs

API & Deployment Pricing

Open-weights model available for local and private cloud deployment. Compute costs depend on the target GPU hardware instance.

Deployment TierPricing Structure
Open Checkpoint Weights$0.00 (Free Download)
Inference Token Consumption$0.00 / Token
Inference Cost & ROI Engine
Market Cloud Rate
Prompt / Input Volume:50M Tokens / mo
1M500M1,000M
Generated / Output Volume:10M Tokens / mo
1M250M500M
Estimated Monthly Spend
$125.00/ mo
Input (50M @ $1.50/1M):$75.00
Output (10M @ $5.00/1M):$50.00
Cloud GPU Breakeven Ratio
RunPod RTX 4090 ($316/mo)0.40x spend
Lambda 1x H100 ($1,800/mo)0.07x spend
💡 Open-weights model. You can self-host for $0 token API charge or consume via managed serverless endpoints at the rates shown above.
Similar Frontier Models & Alternatives
Explore All Comparisons

Comparable Foundation Architectures

Alternative models in the Video class with similar capabilities, context windows, or deployment profiles.

Alibaba CloudVideo

Qwen3.8 Flash Next

Context:262k ctx
Parameters:Open Weights
Input Rate:Free / Self-Host
Zhipu AIVideo

GLM-5.3-Flash

Context:1000k ctx
Parameters:Proprietary
Input Rate:Free / Self-Host
Alibaba CloudVideo

Qwen3.8 Flash

Context:1000k ctx
Parameters:Proprietary
Input Rate:$0.15/1M
Integration & Deployment
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("STEPFUN_KEY", "EMPTY"),
    base_url="http://localhost:8000/v1"
)

response = client.chat.completions.create(
    model="stepfun-step-3.7-flash",
    messages=[{"role": "user", "content": "Explain quantum superposition in 2 sentences."}]
)
print(response.choices[0].message.content)
Frequently Asked Questions

Frequently Asked Questions about Step 3.7 Flash

Essential facts, architectural specs, hardware constraints, and pricing answers for Step 3.7 Flash.

To run Step 3.7 Flash (Open Weights) locally, you generally need Depends on quantization. We recommend using quantized GGUF/AWQ formats with Ollama or vLLM to optimize memory footprint.

Primary Sources & Access Repositories

All technical specifications, parameter distributions, context architectures, and benchmark evaluations for Step 3.7 Flash are audited against primary source release documentation, research whitepapers, and verified vendor API endpoints.

api id:stepfun/step-3.7-flash
knowledge cutoff:2026-03-01