Step 3.7 Flash

zenmux/stepfun/step-3.7-flash · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideo.

$0.44Blended $/1M (3:1)

$0.2Input $/1M

$1.15Output $/1M

$1.351M in + 1M out

—Cache read $/1M

#2021 of 5,000Cheapest rank

Provider: ZenMux (zenmux)
Context: 256,000 tokens
Max output: 256,000 tokens
Capabilities: toolsreasoningtextimagevideo

Same model, other providers

“Step 3.7 Flash” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Nvidia	free	free	$0.00	256k
UnoRouter	free	free	$0.00	256k
StepFun (Global)	$0.185	$1.11	$0.42	256k
StepFun (China)	$0.185	$1.11	$0.42	256k
Ambient	$0.19	$1.14	$0.43	262k
ZenMux (this)	$0.2	$1.15	$0.44	256k
EmpirioLabs AI	$0.2	$1.15	$0.44	256k
Kilo Gateway	$0.2	$1.15	$0.44	256k
Vercel AI Gateway	$0.2	$1.15	$0.44	256k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at ZenMux and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"stepfun/step-3.7-flash","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):