Model pricing
Estimated credits per run. One credit is one US cent. Your settings and output decide the final cost. See plans and credit packs
Image Generation
30 models · ranked on text-to-image
| Model | Cost per run | Rank | Speed |
|---|---|---|---|
| Rembg Background Remover FAL | 0.1 credits | – | Fast |
| Recraft Crisp Upscaler Recraft | 0.5 credits | – | Fast |
| Image Segmentation (SAM 3) Meta | 0.7 credits | – | Fast |
| Muse Image Meta | 1 credit | 3 | Fast |
| Bria Background Remover BRIA AI | 2 credits | – | Fast |
| Grok Imagine Image XAI | 3 credits | 13 | Fast |
| FLUX.2 Klein 9B Image Generator Black Forest Labs | 2–4 credits | – | Fast |
| Z-Image Generator Alibaba Cloud | up to 7 credits | 12 | Fast |
| FLUX.2 Turbo Image Generator Black Forest Labs | 0.3–9 credits | – | Fast |
| Seedream 5.0 Lite ByteDance | 5 credits | 11 | Fast |
| Seedream V4.5 ByteDance | 5 credits | 9 | Fast |
| Krea 2 Image Generator Krea | 4–9 credits | 8 | Fast |
| MAI Image 2.5 Generator Microsoft | 7–8 credits | 6 | Medium |
| P-Image Upscale Pruna AI | 0.7–16 credits | – | Fast |
| Nano Banana 2.1 Google DeepMind | 5–15 credits | – | – |
| Seedream 5.0 Pro ByteDance | 6–16 credits | – | Very slow |
| Ideogram Layerize Text Ideogram | 12 credits | – | Medium |
| Gemini 3.1 Flash Image Generator Google DeepMind | 6–20 credits | 1 | Fast |
| Ideogram V4.5 Ideogram | 1–30 credits | 2 | – |
| Phota Image Editor FAL | 12–24 credits | – | Fast |
| FLUX.2 Pro Image Generator Black Forest Labs | up to 49 credits | 4 | Fast |
| Quiver AI Image to SVG Quiver AI | 7–45 credits | – | Slow |
| Nano Banana Pro Image Generator Google DeepMind | 18–34 credits | 5 | Fast |
| Quiver AI SVG Generator Quiver AI | 7–48 credits | – | Slow |
| FLUX.2 Pro Outpaint Black Forest Labs | 6–55 credits | – | Medium |
| GPT Image 2.5 OpenAI | 0.7–73 credits | – | Fast |
| FLUX 3 Image Black Forest Labs | 6–82 credits | – | – |
| FLUX.2 Flex Image Generator Black Forest Labs | up to 99 credits | 10 | Fast |
| FLUX.2 Max Image Generator Black Forest Labs | up to 115 credits | 7 | Fast |
| Clarity Upscaler FAL | 4–271 credits | – | Fast |
Video Generation
40 models · ranked on image-to-video
| Model | Cost per run | Rank | Speed |
|---|---|---|---|
| Edit Video (FLUX.3) Black Forest Labs | 4–61 credits | – | Fast |
| Edit Video (Grok Imagine) XAI | 8–86 credits | – | Fast |
| Hailuo H3 Max Turbo (MiniMax) MiniMax | 17–81 credits | 11 | Fast |
| Reference to Video (Grok Imagine) XAI | 7–95 credits | 12 | Fast |
| P-Video Pruna AI | 0.7–108 credits | 10 | Fast |
| PixVerse V6 Image-to-Video PixVerse | 6–124 credits | 3 | Fast |
| PixVerse V6 Transition PixVerse | 6–124 credits | – | Fast |
| Image to Video (Kling 2.5 Pro) Kuaishou Technology | 47–95 credits | 20 | Fast |
| Grok Imagine Video XAI | 7–142 credits | 22 | Fast |
| Seedance 2.0 Mini Reference ByteDance | 6–153 credits | – | Fast |
| Seedance 2.0 Mini ByteDance | 10–153 credits | 18 | Fast |
| Seedance Pro 1.5 ByteDance | 3–189 credits | 19 | Fast |
| Remove Video Background (VEED Fast) VEED | 1–194 credits | – | Fast |
| Image to Video (Kling 2.6 Pro) Kuaishou Technology | 47–189 credits | 8 | Fast |
| Seedance 2.0 Fast Reference ByteDance | 10–245 credits | – | Fast |
| Seedance 2.0 Fast ByteDance | 16–245 credits | 9 | Fast |
| Image to Video (Kling V3 Standard) Kuaishou Technology | 34–255 credits | 6 | Medium |
| Edit Video (Kling O3 Pro) Kuaishou Technology | 68–227 credits | – | Medium |
| Grok Imagine Video 1.5 XAI | 12–285 credits | 14 | Fast |
| Motion Control (Kling V3) Kuaishou Technology | 85–227 credits | – | Very slow |
| Image to Video (Kling O3 Pro) Kuaishou Technology | 45–284 credits | 17 | Medium |
| Reference to Video (Kling O3 Pro) Kuaishou Technology | 45–284 credits | 13 | Very slow |
| Image to Video (Kling V3 Pro) Kuaishou Technology | 45–340 credits | 23 | Fast |
| Edit Video (Gemini Omni Flash 1.1) Google DeepMind | 14–492 credits | – | Fast |
| Gemini Omni Flash 1.1 Google DeepMind | 14–492 credits | 16 | Fast |
| Reference to Video (Gemini Omni Flash 1.1) Google DeepMind | 14–492 credits | 24 | Fast |
| Hailuo H3 Max (MiniMax) MiniMax | 34–481 credits | 5 | Fast |
| Seedance 2.0 Reference ByteDance | 13–758 credits | – | Medium |
| Seedance 2.0 ByteDance | 20–758 credits | 7 | Medium |
| Remove Video Watermark WaveSpeedAI | 7–810 credits | – | Fast |
| Wan 3.0 Alibaba Cloud | 14–810 credits | 2 | Medium |
| Wan 3.0 Reference Alibaba Cloud | 14–810 credits | 1 | Medium |
| FLUX.3 Black Forest Labs | 115–783 credits | 15 | Medium |
| FLUX.3 Keyframes Black Forest Labs | 115–783 credits | – | Medium |
| Image to Video (Kling V3 4K) Kuaishou Technology | 170–851 credits | 21 | Medium |
| Topaz Video Upscale Topaz Labs | 7–1,053 credits | – | Medium |
| Extend Video (FLUX.3) Black Forest Labs | 277–1,431 credits | – | Fast |
| Seedance 2.5 Reference ByteDance | 19–3,023 credits | – | Medium |
| Seedance 2.5 ByteDance | 31–3,023 credits | 4 | Slow |
| Add Video Subtitles (VEED) VEED | 14–3,240 credits | – | Fast |
Audio Generation
17 models · ranked on text-to-music
| Model | Cost per run | Rank | Speed |
|---|---|---|---|
| Create Voice (Kling) Kuaishou Technology | 0.9 credits | – | – |
| Kokoro Text to Speech Hexgrad | 1 credit | – | Fast |
| Zonos Text to Speech Zyphra | 1 credit | – | Slow |
| Transcribe Audio (Whisper) OpenAI | 0.2–6 credits | – | Fast |
| Generate Sound Effects ElevenLabs | 0.1–8 credits | – | Very slow |
| Generate Music (Lyria 3) Google DeepMind | 5–11 credits | – | Fast |
| Google Gemini Text to Speech Google DeepMind | 0.2–24 credits | – | Fast |
| ElevenLabs V4 Text to Speech ElevenLabs | 1–32 credits | – | Fast |
| Generate Music (MiniMax v2.6) MiniMax | 20 credits | – | Very slow |
| Transcribe Audio (ElevenLabs Scribe) ElevenLabs | up to 46 credits | – | Fast |
| Split Audio (LALAL.AI) LALAL.AI | 4–43 credits | – | – |
| Separate Audio (SAM Audio) Meta | 7–54 credits | – | Medium |
| Seed Audio 1.0 Text to Speech ByteDance | 3–66 credits | – | Medium |
| Speech to Speech (ElevenLabs) ElevenLabs | 1–81 credits | – | Fast |
| Fish Audio Text to Speech Fish Audio | 0.2–91 credits | – | Fast |
| Video to Sound Effects (Mirelo) Mirelo | 7–89 credits | – | – |
| Generate Music (ElevenLabs) ElevenLabs | 3–101 credits | – | Fast |
Language models (LLMs)
2 models
| Model | Cost per run | Speed |
|---|---|---|
| Analyze Media Google DeepMind | 0.6–6 credits | – |
| Claude Sonnet 4.6 (Text Generation) Anthropic | 2–24 credits | – |
Cost sorting uses the middle of each price range. Speed labels are rough historical estimates, not measured seconds. A dash means not ranked or not measured yet.
Figures are estimates for a single run. They leave out what the model can’t predict, such as how many reference images you attach. Your credit history shows the exact cost of every run.