Phersa runs Nano Banana 2 and Gemini Omni 1.1 Flash on your own Google AI Studio (Gemini API) key. Google bills your Google Cloud project at its published rates, and Phersa adds no markup.
Get your Google AI Studio API key
aistudio.google.com/apikey Open | Model | Setting | Price |
|---|---|---|
| Nano Banana 2 Up to 14 reference images | 1K | $0.067 |
| 2K | $0.101 | |
| 4K | $0.151 | |
| Gemini Omni 1.1 Flash 3–10 s clipsUp to 6 reference images | 720p · 8 s clip | $0.808 ($0.101/s × 8s) |
| 1080p · 8 s clip | $1.216 ($0.152/s × 8s) | |
| 4K · 8 s clip | $2.432 ($0.304/s × 8s) |
Each model's price on Google AI Studio next to the cheapest other providers Phersa supports. Video is priced for an 8-second clip without reference images.
| Provider | 1K | 2K | 4K |
|---|---|---|---|
| Google AI Studio | $0.067 | $0.101 | $0.151 |
| Kie | 8 creditsLowest $0.04 | 12 creditsLowest $0.06 | 18 creditsLowest $0.09 |
| WaveSpeedAI | $0.07 | $0.105 | $0.14 |
Kie is cheapest at 1K, 2K and 4K: $0.04, $0.06 and $0.09, vs $0.067, $0.101 and $0.151 on Google AI Studio.
Also on Agent Platform, fal, Atlas Cloud and Krea, at the same or higher prices.
| Provider | 720p · 8 s | 1080p · 8 s | 4K · 8 s |
|---|---|---|---|
| Google AI Studio | $0.808 $0.101/s × 8s | $1.216 $0.152/s × 8s | $2.432 $0.304/s × 8s |
| Kie | 105 creditsLowest $0.525 | 105 creditsLowest $0.525 | 189 creditsLowest $0.945 |
| fal, WaveSpeedAI and Krea | $0.80 $0.10/s × 8s | $1.20 $0.15/s × 8s | $2.40 $0.30/s × 8s |
| Atlas Cloud | $0.792 $0.099/s × 8s | $1.152 $0.144/s × 8s | $2.232 $0.279/s × 8s |
Kie is cheapest at 720p, 1080p and 4K for an 8-second clip: $0.525–$0.945, vs $0.808, $1.216 and $2.432 on Google AI Studio.
Also on Agent Platform, at the same or higher prices.
Sign in at aistudio.google.com, open API keys and create a key. New keys start with AQ. The key belongs to a Google Cloud project, and Google bills generations to that project. Prices on this page are Google's paid (Standard tier) rates.
aistudio.google.com/apikey →In Phersa, open Settings, go to API keys and choose Google AI Studio. Paste the key and click Save & verify.
Phersa checks the key format, then tests the key with Google. A key Google rejects is not stored, and saved keys are encrypted.
In the app, pick Nano Banana 2 or Gemini Omni 1.1 Flash on Google AI Studio. You see the cost in dollars before you generate, such as $0.067 for a 1K Nano Banana 2 image.
Google AI Studio is Google's developer tool for building with Gemini models and creating Gemini API keys. Every Gemini API key belongs to a Google Cloud project, which handles billing and permissions. It is separate from Gemini Enterprise Agent Platform, formerly Vertex AI.
Visit Google AI Studio ↗On Google AI Studio, Nano Banana 2 costs $0.067 for a 1K image, $0.101 for 2K and $0.151 for 4K. That is Google's image output rate; input tokens add a little on top.
No. Generations bill to your own Google Cloud project at Google's published rates, and Phersa adds no markup. The Phersa plan is a separate $99 per month.
See Phersa pricing →Partly. The Gemini API free tier has rate limits, and Google may use that content to improve its products, but Nano Banana 2 and Gemini Omni 1.1 Flash are paid tier only. The $300 Google Cloud trial cannot pay for it. Terms can change.
Check Gemini API pricing ↗Nano Banana 2 and Gemini Omni 1.1 Flash. GPT Image 2.5 Sunburst, Grok Imagine Image 2.0 and Grok Imagine Video 1.5 run on other providers, such as Kie and fal. Voice Swap needs an ElevenLabs key.
Voice Swap with ElevenLabs →Create a key at aistudio.google.com/apikey. In Phersa, open Settings, go to API keys, choose Google AI Studio and paste it. Phersa checks the key with Google before saving it.
See the setup steps →No. Kie is cheaper at every setting (Kie vs Google AI Studio): $0.04 vs $0.067 at 1K, $0.06 vs $0.101 at 2K and $0.09 vs $0.151 at 4K.
See Kie prices →Both run Nano Banana 2 and Gemini Omni 1.1 Flash at the same prices in Phersa. Google AI Studio needs only an API key. Agent Platform (formerly Vertex AI) uses a Google Cloud service account, which suits teams that already run Google Cloud.
See Agent Platform →New Google AI Studio keys start with AQ. Older keys start with AIza; Phersa still accepts them, but Google is retiring that format, so create a new key if yours stops working.
Google answered that the Google Cloud project behind your key cannot use that model. Check the project's access to the model in Google AI Studio, or create a key in a project that has it, then generate again.
Phersa tests the key with Google before saving it, stores it encrypted and uses it only for generation. AI agents connected over MCP cannot read or change it. Removing the key in Settings deletes it permanently.
