Question 1

What is Step 3.7 Flash?

Accepted Answer

Step 3.7 Flash is a model from StepFun, released on May 29, 2026. Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning. Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks.

Question 2

How much does Step 3.7 Flash cost?

Accepted Answer

On the Respan gateway, input starts at $0.18 per 1M tokens on Novita, and output starts at $1.03 per 1M tokens on Novita, after gateway discounts. Averaged across 3 providers, it costs $0.19 per 1M input tokens and $1.11 per 1M output tokens.

Question 3

Which providers serve Step 3.7 Flash on Respan?

Accepted Answer

3 providers serve Step 3.7 Flash: Novita, OpenRouter, and EmpirioLabs.

Question 4

What is Step 3.7 Flash's context window?

Accepted Answer

Step 3.7 Flash accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Step 3.7 Flash with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "step-3.7-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Step 3.7 Flash?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 75 tokens per second, and the lowest response latency was 1.5 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Step 3.7 Flash score on benchmarks?

Accepted Answer

Step 3.7 Flash has 19 published benchmark scores, including SWE-bench Verified 76.5%, DeepSearchQA F1 92.8%, and AA-LCR 63.9%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
NovitaSave 10%`novita/stepfun/step-3.7-flash`	262K	$0.18/M	$1.03/M
OpenRouter`openrouter/stepfun/step-3.7-flash`	262K	$0.20/M	$1.15/M
EmpirioLabs`empiriolabs/step-3-7-flash`	256K	$0.20/M	$1.15/M

Step 3.7 Flash

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Coding4

Agents8

Reasoning3

Math1

Multimodal3

Apps

Step 3.7 Flash FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.