Official API Model ID (SDK String): step-3-7-flash
Supported SDK & API Protocol: OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Lifecycle & Deprecation Status: Active GA (Guaranteed support through 2028+)
Production Rate Limits (RPM & TPM): Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Pricing Tier (>128K / >200K): Free across full context window (only KV-cache VRAM scales)
Prompt Cache Write & TTL Policy: Automatic prefix KV-caching in vLLM / SGLang (0 cost)
Computer Use & Browser GUI Agent: API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling: Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Code Sandbox: Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Fine-Tuning & Distillation Support: Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
Multimodal Tokenization Billing: Text BPE (~4 chars/token)
Weights Precision & Quantization: BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
Minimum GPU VRAM Requirement: 43 GB VRAM (4-bit Quantized) · 151 GB VRAM (Native BF16)
Supported Inference Engines: vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
System Card & Safety Framework: Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
Enterprise Compliance (SOC2 / HIPAA / ZDR): 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control

Engineering & Pricing Workbench

Step 3.7 Flash Cost, Context, Hardware & API Integration

Daily API Requests:500 / day

Avg Input Tokens per Request:4,000 tok

Avg Output Tokens per Request:1,000 tok

Conversation Depth (History Re-billing):1 Turn (Single-Shot)

Prompt Cache Hit Rate:($0/1M cached)50%

Estimated Monthly API Cost (30 Days)

Free ($0)

Daily Cost:: $0.00
Cost per Request:: $0.00000
Effective Input / 1M:: $0.000
Effective Output / 1M:: $0.000

Subscription ($20/mo) vs API

Open-weights or free-tier model: $0 API license cost when self-hosted.

Same Monthly Workload Cost Across Popular Reference Models

Step 3.7 Flash (Active)

$0.00

/ month

Gemini 2.5 Flash

$18.00

/ month

DeepSeek V3

$32.70

/ month

GPT-4o

$300.00

/ month

Claude 3.7 Sonnet

$405.00

/ month

Live Prompt Paste Tokenizer & Cost Counter

Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.

Chars / Words

175 / 24

OpenAI o200k

~46 tok

Claude BPE

~49 tok

Llama / DeepSeek

~51 tok

Hybrid Prompt Routing Cascade Simulator

Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Step 3.7 Flash:

Cascaded Monthly Bill:$13.50/mo

This model is already priced at or below the fast router baseline.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia

Step 3.7 Flash2026 Frontier Median

MMLU-Pro: 73%
HumanEval: 84%
Chatbot Arena Elo: 1275pts

Strengths

Exceptional generation throughput (160 tps) with sub-300ms initial response
Spacious 256K context window available with open weights
Optimized for rapid dialogue loops and low-latency agent orchestration

Limitations & Trade-offs

Reasoning ceiling is lower than dense frontier models on Olympiad STEM
Less specialized in esoteric programming languages

Editorial Assessment

A speedy open-weights reasoner that prioritizes turnaround speed without sacrificing coherence.

Best for: Fast interactive chatbots, rapid agent action loops, and high-frequency classification

Compare Step 3.7 Flash

Step 3.7 Flash vs Command A Plus Step 3.7 Flash vs Qwen3.6 27B Step 3.7 Flash vs Gemini 4 Argon Step 3.7 Flash vs GPT-6 Astra Step 3.7 Flash vs Claude Opus 5.5 Step 3.7 Flash vs GPT-6.1 Sol

Frequently Asked Questions about Step 3.7 Flash

How much does the Step 3.7 Flash API cost per 1M tokens?+

Step 3.7 Flash by StepFun is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.

Should I use a $20/month subscription or the Step 3.7 Flash pay-as-you-go API?+

A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.

How many words and pages fit in Step 3.7 Flash's context window?+

Step 3.7 Flash features a 256K tokens context window, which equals approximately 192,000 English words or ~512 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 8,192 tokens.

Can I run Step 3.7 Flash locally on my own GPU (Open Weights)?+

Yes, Step 3.7 Flash (Confidential / 70B MoE) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.

Does StepFun train on data sent to the Step 3.7 Flash API, and is commercial use allowed?+

100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.

How does Step 3.7 Flash perform on coding and reasoning benchmarks?+

Step 3.7 Flash achieves a composite Intelligence Index of 76/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 73% on MMLU-Pro, and 1275 pts on Chatbot Arena Elo.

What is Step 3.7 Flash best used for?+

Step 3.7 Flash is best suited for: Fast interactive chatbots, rapid agent action loops, and high-frequency classification. Assessment: A speedy open-weights reasoner that prioritizes turnaround speed without sacrificing coherence.

AI Glossary & Architecture Concepts

View full glossary →

Key machine learning concepts and benchmarks relevant to Step 3.7 Flash:

Token

The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.

Benchmark

A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.

Context Window

The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.

Reasoning Model

An AI model trained via reinforcement learning to spend dynamic compute thinking through complex logic, math, and architectural problems before outputting a solution. Examples include OpenAI o1, o3, and DeepSeek R1.

Chain-of-Thought (CoT)

A step-by-step reasoning technique where an AI model generates intermediate problem-solving thoughts before arriving at a final answer. Native reasoning models like OpenAI o3 and DeepSeek R1 use CoT to solve complex math and coding challenges.

Tool Calling

The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.

← Back to all models

Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.

Sources: StepFun Open Weights Hub↗