jishie

Nano Banana 2

openrouter/google/gemini-3.1-flash-image · family gemini-flash · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: reasoningtextimage.

$1.13Blended $/1M (3:1)
$0.5Input $/1M
$3Output $/1M
$3.501M in + 1M out
Cache read $/1M
#3349 of 5,000Cheapest rank
Provider
OpenRouter (openrouter)
Context
131,072 tokens
Max output
32,768 tokens
Capabilities
reasoningtextimage

Same model, other providers

“Nano Banana 2” is offered by 7 providers — cheapest-effective first. This one (OpenRouter) is the cheapest.

ProviderInputOutputBlendedContext
OpenRouter (this)$0.5$3$1.13131k
FastRouter$0.5$3$1.1366k
Abacus$0.5$3$1.131049k
Kilo Gateway$0.5$3$1.1366k
Kilo Gateway$0.5$3$1.13131k
Vercel AI Gateway$0.5$3$1.13131k
OpenRouter$0.5$3$1.1366k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3.1-flash-image","messages":[{"role":"user","content":"hello"}]}'

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