Nano Banana
google/gemini-2.5-flash-image · family gemini-flash · in: text, image → out: text, image · price provider-declared (via models.dev). Capabilities: reasoning text image.
$7.72
Blended $/1M (3:1)
$0.3
Input $/1M
$30
Output $/1M
$30.30
1M in + 1M out
$0.075 −75%
Cache read $/1M
#6945 of 7,708
Cheapest rank
- Provider
- Google (
google) - Kind
- text (outputs text, image)
- Context
- 32,768 tokens
- Max output
- 32,768 tokens
- Capabilities
- reasoning text image
Same model, other providers
“Nano Banana” is offered by 6 providers — cheapest-effective first. Kilo Gateway is the cheapest at $0.42 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kilo Gateway | $0.15 | $1.25 | $0.42 | 33k |
| OpenRouter | $0.3 | $2.5 | $0.85 | 33k |
| Eden AI | $0.3 | $2.5 | $0.85 | 33k |
| Google (this) | $0.3 | $30 | $7.72 | 33k |
| Abacus | $0.3 | $30 | $7.72 | 33k |
| Vertex | $0.3 | $30 | $7.72 | 33k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Google and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gemini-2.5-flash-image","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):