LLM Perks

Step 3.7 Flash

StepFun · All Step models
Free right now Small
ReasoningLong contextOpen weights

Step 3.7 Flash is a language model from StepFun. It is currently free at 1 provider with up to 262K tokens of context. The model supports step-by-step reasoning. Its weights are open, so it can also run locally.

Developer
StepFun
Context
262K tokens
Type
Text
License
Open weights

Where to use Step 3.7 Flash for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
Nous Portal
stepfun/step-3.7-flash:free
262K The $0 Portal plan includes free models with standard rate limits. Model availability can change. No Open

Quick start

curl https://inference-api.nousresearch.com/v1/chat/completions \
  -H "Authorization: Bearer $NOUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepfun/step-3.7-flash:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for Nous Portal. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
19.5
GPQA Diamond
80.9%
Humanity's Last Exam
21.4%
Terminal-Bench Hard
35.6%
τ²-Bench
98.5%
Long context (LCR)
73.7%

Source: Artificial Analysis · Step 3.7 Flash

Similar free models

FAQ

Is Step 3.7 Flash free?

Yes. As of September 26, 2026, Step 3.7 Flash is free at Nous Portal. Each provider has its own limits — see the table above.

What is the context window of Step 3.7 Flash?

The largest context among free routes is 262,144 tokens. Some providers cap it lower.

How do I call Step 3.7 Flash via API?

Use any OpenAI-compatible client with base URL https://inference-api.nousresearch.com/v1, model ID stepfun/step-3.7-flash:free, and a Nous Portal key.

How good is Step 3.7 Flash?

Artificial Analysis Intelligence Index: 19.5, GPQA Diamond: 81%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Step 3.7 Flash open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.