Nano Banana 2 Lite
google-vertex/gemini-3.1-flash-lite-image · family gemini-flash-lite · in: text, image → out: text, image · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$7.69
Blended $/1M (3:1)
$0.25
Input $/1M
$30
Output $/1M
$30.25
1M in + 1M out
$0.025 −90%
Cache read $/1M
#7207 of 8,005
Cheapest rank
- Provider
- Vertex (
google-vertex) - Kind
- text (outputs text, image)
- Context
- 65,536 tokens
- Max output
- 4,096 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Nano Banana 2 Lite” is offered by 7 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kenari | free | free | $0.00 | 66k |
| Kilo Gateway | $0.25 | $1.5 | $0.56 | 66k |
| OpenRouter | $0.25 | $1.5 | $0.56 | 66k |
| AIHubMix | $0.25 | $1.5 | $0.56 | 66k |
| Eden AI | $0.25 | $1.5 | $0.56 | 66k |
| Vertex (this) | $0.25 | $30 | $7.69 | 66k |
| $0.25 | $30 | $7.69 | 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-3.1-flash-lite-image","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):