Nano Banana Pro

google-vertex/gemini-3-pro-image · family gemini-pro · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: reasoningtextimage.

$31.50Blended $/1M (3:1)

$2Input $/1M

$120Output $/1M

$122.001M in + 1M out

—Cache read $/1M

—Cheapest rank

Provider: Vertex (google-vertex)
Context: 65,536 tokens
Max output: 32,768 tokens
Capabilities: reasoningtextimage

Same model, other providers

“Nano Banana Pro” is offered by 8 providers — cheapest-effective first. FastRouter is the cheapest at $4.50 blended.

Provider	Input	Output	Blended	Context
FastRouter	$2	$12	$4.50	66k
Abacus	$2	$12	$4.50	66k
Kilo Gateway	$2	$12	$4.50	66k
Kilo Gateway	$2	$12	$4.50	66k
Vercel AI Gateway	$2	$12	$4.50	66k
OpenRouter	$2	$12	$4.50	66k
OpenRouter	$2	$12	$4.50	131k
Vertex (this)	$2	$120	$31.50	66k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemini-3-pro-image","messages":[{"role":"user","content":"hello"}]}'

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