Speed
Output tokens / second
Step 3.7 Flash overview
Step 3.7 Flash by StepFun
A multimodal Mixture-of-Experts model from StepFun with native image and video understanding, optimized for fast inference, reasoning, and agent workflows with a 256K context window.
Step 3.7 Flash specs
- Model ID
stepfun/step-3.7-flash- Developer
- StepFun
- Context window
- 256,000 tokens
- Max output
- 256,000 tokens
- Input
- Text, Image, Video
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What exactly is Step 3.7 Flash?
Step 3.7 Flash is StepFun's latest multimodal Mixture-of-Experts model, built for agentic coding, visual understanding, and long-context tasks. It pairs a 196B-parameter language backbone with a 1.8B Vision Transformer encoder for native image and video processing.
The MoE architecture activates approximately 11B parameters per token during inference, keeping compute cost close to an 11B dense model while maintaining a 198B total parameter budget. The model ships with selectable reasoning depth, tool use, and multimodal fusion as production defaults.
Architecture: what makes it fast and capable
Use cases
Step 3.7 Flash is documented as suited to simple Q&A, summarization, rewriting, and information extraction. It is also suited to general reasoning and multi-step tasks.
The model is documented for complex reasoning, math, planning, and code analysis. It is also suited to code generation, file editing, and complex task coordination in terminal, IDE, or agent workflows.
It is documented for multimodal tasks such as image understanding, image-text-to-text, and video-text-to-text workflows. It is also intended for GUI-oriented tasks that use text, screenshots, or images as input.
The model is documented for agentic workflows that combine perception, search, and reasoning, including tool calling and stable structured outputs.
Capabilities
- Function calling
- Streaming
- Structured outputs
- Reasoning
Step 3.7 Flash benchmarks by 
Artificial Analysis
See how Step 3.7 Flash compares in generation speed and latency. Data retrieved Nov 3, 2026.
Benchmark results
Compare 16 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
AA-LCR
Reasoning across long documents of about 100k tokens.
SciCode
Python coding tasks drawn from scientific research.
IFBench
Following precise instructions about the shape of the answer.
Step 3.7 Flash API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.2116 | 1M tokens |
| Output | $1.22 | 1M tokens |
| Cached input | $0.0423 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Step 3.7 Flash vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Step 3.7 Flash | $0.2116 | $1.22 |
 DeepSeek Chat (V4.1 Flash) | $0.3 | $1.2 |
| DeepSeek-R1 | $0.3 | $1.2 |
| DeepSeek-V3 | $0.3068 | $1.21 |
| Step 5 Preview | $1.06 | $2.86 |
How to use the Step 3.7 Flash API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "stepfun/step-3.7-flash",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "stepfun/step-3.7-flash",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "stepfun/step-3.7-flash",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Step 3.7 Flash
Related articles
Step 3.7 Flash FAQ
What is the context window of Step 3.7 Flash?
Step 3.7 Flash has a 256,000 tokens context window and can return up to 256,000 tokens.
What inputs and outputs does Step 3.7 Flash support?
Step 3.7 Flash takes image, text, video as input and returns text.
What is the model ID for Step 3.7 Flash?
Use stepfun/step-3.7-flash as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
When was Step 3.7 Flash released?
Step 3.7 Flash became available on June 1, 2026.
How much does Step 3.7 Flash cost?
Step 3.7 Flash costs $0.2116 input and $1.22 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does Step 3.7 Flash support streaming?
Yes, Step 3.7 Flash can stream responses as they are generated.
Can Step 3.7 Flash read images?
Yes, Step 3.7 Flash accepts image input alongside text.
Who created Step 3.7 Flash?
Step 3.7 Flash was built by StepFun.
Is Step 3.7 Flash capable of reasoning?
Yes, its capabilities include reasoning alongside function calling and structured outputs.
Can Step 3.7 Flash call external tools or functions?
Yes, it supports function calling, tool use, and parallel tool calls.