Step 3.7 Flash

stepfun-ai/step-3.7-flash

Step 3.7 Flash is a 198B mixture-of-experts model with roughly 11B active per token, built for high-throughput agent work. Its attention is mostly sliding-window, so generation speed holds steady as the conversation grows rather than degrading with length. It accepts image input through a native vision encoder, supports a 256K context window, three selectable reasoning depths, and tool calling. Suited to search loops, long document work and concurrent coding agents that need to read what is on screen.

Get an API key

Endpoints

Each row is one provider serving these weights at one precision. Prices are per million tokens.

Provider	Quantisation	Context	Max out	Input	Output	Cached in
Infersia	NVFP4	256K	32K	$0.18	$1.05	$0.04

Prefix caching is enabled and the discount is passed through. If your agent replays the same system prompt each iteration, the repeated portion bills at the cached rate.

Agent config

Paste this into your coding agent and it can configure itself. The timeout is derived from this variant's measured throughput, not a guess — a long generation that outlives a client's default ceiling is the most common way a working request looks broken.

# Infersia — stepfun-ai/step-3.7-flash
# Paste this to your agent. Values are measured, not aspirational.

provider:
  type: openai-compatible
  base_url: https://api.infersia.com/v1
  api_key: ${INFERSIA_API_KEY}   # from https://infersia.com/dashboard/keys
  model: stepfun-ai/step-3.7-flash

limits:
  max_input_tokens: 262144      # hard limit — over this returns HTTP 413
  max_output_tokens: 32768
  timeout_seconds: 420                   # covers the full 32768 output budget at 163 tok/s, doubled for the tail
  # allow ~13s per 1,000 output tokens if you cap max_tokens lower

features:
  streaming: true
  tools: true
  vision: true
  reasoning: true   # OFF by default; send chat_template_kwargs.enable_thinking=true to opt in
  prompt_caching: true   # automatic; reuse a stable prefix and it bills at the cache rate

pricing_usd_per_million_tokens:
  input: 0.18
  output: 1.05
  cached_input: 0.036

What NVFP4 means

Custom quantisation.

The quantisation is returned on every request in the x-infersia-quantization response header — so you can assert on it in your own tests rather than trusting this page.

Call it

curlbash

curl https://api.infersia.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERSIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepfun-ai/step-3.7-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Pin a provider with stepfun-ai/step-3.7-flash@infersia, or take the cheapest with the bare id. Add :free for the rate-limited free tier where one exists.