Nano Banana Pro
aihubmix/gemini-3-pro-image · family gemini-pro · in: text, image → out: text, image · price provider-declared (via models.dev). Capabilities: reasoning text image.
$31.50
Blended $/1M (3:1)
$2
Input $/1M
$120
Output $/1M
$122.00
1M in + 1M out
—
Cache read $/1M
#7908 of 8,005
Cheapest rank
- Provider
- AIHubMix (
aihubmix) - Kind
- text (outputs text, image)
- Context
- 65,536 tokens
- Max output
- 32,768 tokens
- Capabilities
- reasoning text image
Same model, other providers
“Nano Banana Pro” is offered by 10 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 | $2 | $12 | $4.50 | 66k |
| Abacus | $2 | $12 | $4.50 | 66k |
| OpenRouter | $2 | $12 | $4.50 | 131k |
| Vercel AI Gateway | $2 | $12 | $4.50 | 66k |
| Eden AI | $2 | $12 | $4.50 | 66k |
| Requesty | $2 | $12 | $4.50 | 1M |
| AIHubMix (this) | $2 | $120 | $31.50 | 66k |
| $2 | $120 | $31.50 | 131k | |
| Vertex | $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 AIHubMix 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):