Nano Banana Pro
As of Oct 4, 2026, the cheapest Nano Banana Pro API price is $1 per 1M input tokens (Kilo Gateway) and $6 per 1M output tokens (Kilo Gateway). Nano Banana Pro is offered by 11 providers in the gemini-pro family, reasoning enabled. Google's own rate is $120 per 1M output tokens.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| Kilo Gateway | Cheapest$1 | Cheapest$6 | $0.1 | $0.1875 | 66k |
| Abacus | $2 | $12 | $0.2 | — | 66k |
| Abacus | $2 | $12 | $0.2 | — | 66k |
| Eden AI | $2 | $12 | $0.2 | $0.375 | 66k |
| Eden AI | $2 | $12 | $0.2 | $0.375 | 66k |
| Eden AI | $2 | $12 | $0.2 | $0.375 | 66k |
| FastRouter | $2 | $12 | — | — | 66k |
| Kilo Gateway | $2 | $12 | $0.2 | $0.375 | 66k |
| OpenRouter | $2 | $12 | $0.2 | $0.375 | 131k |
| OpenRouter | $2 | $12 | $0.2 | $0.375 | 66k |
| Poe | $2 | $12 | $0.2 | — | 66k |
| Requesty | $2 | $12 | $0.2 | $4.5 | 1.0M |
| Vercel AI Gateway | $2 | $12 | $0.2 | — | 66k |
| AIHubMix | $2 | $120 | — | — | 66k |
| $2 | $120 | — | — | 66k | |
| $2 | $120 | — | — | 131k | |
| Vertex | $2 | $120 | $0.2 | — | 66k |
Nano Banana Pro pricing FAQ
What is the cheapest Nano Banana Pro API?
As of Oct 4, 2026, Kilo Gateway has the lowest Nano Banana Pro output price at $6 per 1M tokens, and Kilo Gateway has the lowest input price at $1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How much does Nano Banana Pro cost on Google?
Google charges $2 per 1M input tokens and $120 per 1M output tokens for Nano Banana Pro.
How many providers offer Nano Banana Pro?
11 providers list Nano Banana Pro on Sovyron; 17 of them sell it at a metered per-token price.
Is Nano Banana Pro free?
No provider in the Sovyron catalog lists a free tier for Nano Banana Pro.
What is the context window of Nano Banana Pro?
Nano Banana Pro supports a 1.0M-token context window and up to 33k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not.
Estimated
—