Phersa runs Nano Banana 2, GPT Image 2.5 Sunburst, Grok Imagine Image 2.0, Gemini Omni 1.1 Flash and Grok Imagine Video 1.5 on your own WaveSpeedAI API key. WaveSpeedAI bills in US dollars, and Phersa adds no markup.
Get your WaveSpeedAI API key
wavespeed.ai/accesskey Open | Model | Setting | Price |
|---|---|---|
| Nano Banana 2 Up to 14 reference images | 1K | $0.07 |
| 2K | $0.105 | |
| 4K | $0.14 | |
| GPT Image 2.5 Sunburst Text to image or image to imageUp to 16 reference images+$0.015 per reference image | 1K · Low | $0.01 |
| 1K · Medium | $0.024 | |
| 1K · High | $0.09 | |
| 1K · Extra high | $0.16 | |
| 1K · Max | $0.36 | |
| 2K · Low | $0.02 | |
| 2K · Medium | $0.04 | |
| 2K · High | $0.15 | |
| 2K · Extra high | $0.27 | |
| 2K · Max | $0.60 | |
| 4K · Low | $0.03 | |
| 4K · Medium | $0.07 | |
| 4K · High | $0.27 | |
| 4K · Extra high | $0.48 | |
| 4K · Max | $1.00 | |
| Grok Imagine Image 2.0 1 reference image+$0.01 per reference image | 1K · Low | $0.05 |
| 2K · Low | $0.05 | |
| 1K · Medium | $0.05 | |
| 2K · Medium | $0.05 | |
| Gemini Omni 1.1 Flash 3–10 s clipsUp to 10 reference images | 720p · 8 s clip | $0.80 ($0.10/s × 8s) |
| 1080p · 8 s clip | $1.20 ($0.15/s × 8s) | |
| 4K · 8 s clip | $2.40 ($0.30/s × 8s) | |
| Grok Imagine Video 1.5 1–15 s clipsUp to 7 reference images+$0.01 per reference image | 720p · 8 s clip | $1.12 ($0.14/s × 8s) |
| 1080p · 8 s clip | $2.00 ($0.25/s × 8s) |
Each model's price on WaveSpeedAI next to the cheapest other providers Phersa supports. Video is priced for an 8-second clip without reference images.
| Provider | 1K | 2K | 4K |
|---|---|---|---|
| WaveSpeedAI | $0.07 | $0.105 | $0.14 |
| Agent Platform and Google AI Studio | $0.067 | $0.101 | $0.151 |
| Kie | 8 creditsLowest $0.04 | 12 creditsLowest $0.06 | 18 creditsLowest $0.09 |
Kie is cheapest at 1K, 2K and 4K: $0.04, $0.06 and $0.09, vs $0.07, $0.105 and $0.14 on WaveSpeedAI.
Also on fal, Atlas Cloud and Krea, at the same or higher prices.
| Provider | 1K · Low | 1K · Medium | 1K · High | 1K · Extra high | 1K · Max | 2K · Low | 2K · Medium | 2K · High | 2K · Extra high | 2K · Max | 4K · Low | 4K · Medium | 4K · High | 4K · Extra high | 4K · Max |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| WaveSpeedAI | $0.01 | $0.024 | $0.09 | $0.16 | $0.36 | $0.02 | $0.04 | $0.15 | $0.27 | $0.60 | $0.03 | $0.07 | $0.27 | $0.48 | $1.00 |
WaveSpeedAI adds $0.015 per reference image. Kie, fal and Atlas Cloud price GPT Image 2.5 Sunburst by other settings: from $0.03 on Kie, from $0.00471 on fal and from $0.00377 on Atlas Cloud. fal bills GPT Image 2.5 Sunburst by tokens at OpenAI's rates. Prices shown are the output image at 9:16 (1152×2048); the prompt and each reference image add input tokens, about $0.008 for a 1024×1024 reference by fal's measurements. Atlas Cloud bills GPT Image 2.5 Sunburst by tokens at 80% of OpenAI's rates. Prices shown are the output image at 9:16 (1152×2048); the prompt and each reference image add input tokens.
| Provider | 1K · Low | 2K · Low | 1K · Medium | 2K · Medium | 1K |
|---|---|---|---|---|---|
| WaveSpeedAI | $0.05 | $0.05Lowest | $0.05Lowest | $0.05Lowest | Not offered |
| Kie | Not offered | Not offered | Not offered | Not offered | 4 credits $0.02 |
| fal, Atlas Cloud and SpaceXAI | $0.04Lowest | $0.06 | $0.06 | $0.08 | Not offered |
| Krea | $0.042 | $0.063 | $0.063 | $0.084 | Not offered |
WaveSpeedAI is lowest at 2K · Low, 1K · Medium and 2K · Medium. fal, Atlas Cloud and SpaceXAI are cheapest at 1K · Low: $0.04, vs $0.05 on WaveSpeedAI. The lowest price overall is 1K on Kie, at $0.02.
WaveSpeedAI, fal, Atlas Cloud and SpaceXAI add $0.01 per reference image. Krea adds $0.0105 per reference image.
| Provider | 720p · 8 s | 1080p · 8 s | 4K · 8 s |
|---|---|---|---|
| WaveSpeedAI | $0.80 $0.10/s × 8s | $1.20 $0.15/s × 8s | $2.40 $0.30/s × 8s |
| Kie | 105 creditsLowest $0.525 | 105 creditsLowest $0.525 | 189 creditsLowest $0.945 |
| 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 $0.80, $1.20 and $2.40 on WaveSpeedAI.
Also on Agent Platform, Google AI Studio, fal and Krea, at the same or higher prices.
| Provider | 720p · 8 s | 1080p · 8 s |
|---|---|---|
| WaveSpeedAI | $1.12 $0.14/s × 8s | $2.00 $0.25/s × 8s |
| Kie | 36 creditsLowest 4.5/s × 8s · $0.18 | 64 creditsLowest 8/s × 8s · $0.32 |
| Atlas Cloud | $0.64 $0.08/s × 8s | $0.64 $0.08/s × 8s |
Kie is cheapest at 720p and 1080p for an 8-second clip: $0.18 and $0.32, vs $1.12 and $2.00 on WaveSpeedAI.
Also on fal, Krea and SpaceXAI, at the same or higher prices.
WaveSpeedAI adds $0.01 per reference image. Kie lists no 1080p rate for Grok Imagine Video 1.5; the Kie 1080p price shown is its rate for the sibling Grok Imagine model.
Sign in at wavespeed.ai, open the access key page and create an API key. WaveSpeedAI takes generation costs from your WaveSpeedAI balance, so add funds to your account too.
wavespeed.ai/accesskey →In Phersa, open Settings, go to API keys and choose WaveSpeedAI. Paste the key and click Save & verify.
Before saving, Phersa tests the key with WaveSpeedAI, and a key WaveSpeedAI rejects is not stored. Saved keys are encrypted, and once connected the WaveSpeedAI panel in Settings shows your balance in dollars.
In the app, pick a model that runs on WaveSpeedAI. You see the cost in dollars before you generate, such as $0.07 for a 1K Nano Banana 2 image.
WaveSpeedAI (wavespeed.ai) is an AI inference platform with one API for 1,000+ image, video and audio models. It bills pay-per-use in US dollars from prepaid credits that never expire. WaveSpeedAI was founded in 2025 and is headquartered in Singapore.
Visit wavespeed.ai ↗On WaveSpeedAI, Nano Banana 2 costs $0.07 for a 1K image, $0.105 for 2K and $0.14 for 4K.
No. Generations bill to your own WaveSpeedAI balance at WaveSpeedAI's price, and Phersa adds no markup. The Phersa plan is a separate $99 per month.
See Phersa pricing →Sometimes. WaveSpeedAI says eligible new users may receive $1 in trial credit with no credit card required, but a new email address alone does not guarantee it, and some premium models are excluded. Terms can change.
Check wavespeed.ai pricing ↗Images: Nano Banana 2, GPT Image 2.5 Sunburst and Grok Imagine Image 2.0. Video: Gemini Omni 1.1 Flash and Grok Imagine Video 1.5. Voice Swap runs on ElevenLabs Voice Changer, so it needs an ElevenLabs key.
Voice Swap with ElevenLabs →Create a key at wavespeed.ai/accesskey. In Phersa, open Settings, go to API keys, choose WaveSpeedAI and paste it. Phersa checks the key with WaveSpeedAI before saving it.
See the setup steps →Yes. WaveSpeedAI is cheaper at every setting (WaveSpeedAI vs fal): $0.07 vs $0.08 at 1K, $0.105 vs $0.12 at 2K and $0.14 vs $0.16 at 4K.
See fal prices →No. On WaveSpeedAI, Grok Imagine Image 2.0 costs $0.05 at every size and quality. On fal, 2K · Medium costs $0.08.
WaveSpeedAI refuses the job, and Phersa shows the error, usually “Out of credits”. Add funds to your WaveSpeedAI account, then generate again.
Phersa tests the key with WaveSpeedAI before saving it, stores it encrypted and uses it for generation and your balance. AI agents connected over MCP cannot read or change it. Removing the key in Settings deletes it permanently.
