vaaya / tools / fal / generate
fal generate for AI agents
Generate or edit images, video, music, and speech via fal.ai.
varies by params per call
npx @vaaya/mcp installParameters
| Param | Type | What |
|---|---|---|
model required | one of 174 values |
Models & pricing
Pass one of these as model, plus that model’s own params. Price is per generated output: a flat figure is per call; ¢/s is per second of video at the model’s default resolution; ¢/MP is per megapixel; TTS is per 1,000 characters. Prices track fal’s published rates and can change with them; provider errors are not charged.
Image
| model | Owner | Type | Price |
|---|---|---|---|
z-image--turbo--tiling | Alibaba | text → image | ~2.4¢/MP |
z-image--turbo--tiling--lora | Alibaba | text → image | ~3¢/MP |
flux-2--klein--4b--edit--lora | Black Forest Labs | image edit | ~1.2¢/MP |
flux-2--klein--4b--lora | Black Forest Labs | text → image | ~1.2¢/MP |
flux-2--klein--9b--edit--lora | Black Forest Labs | image edit | ~1.8¢/MP |
flux-2--klein--9b--lora | Black Forest Labs | text → image | ~1.8¢/MP |
flux-2-pro--outpaint | Black Forest Labs | image edit | 4¢ |
flux-pro--v1--erase | Black Forest Labs | image edit | 4¢ |
flux-pro--v1--vto | Black Forest Labs | image edit | 6¢ |
bytedance--seedream--v5--pro--layerize | ByteDance | image edit | 5¢ |
seedream--v4-5--edit | ByteDance | image edit | 5¢ |
seedream--v4-5--text-to-image | ByteDance | text → image | 5¢ |
seedream--v5-pro--edit | ByteDance | image edit | 17¢ |
seedream--v5-pro--text-to-image | ByteDance | text → image | 17¢ |
google--virtual-try-on | image edit | 10¢ | |
nano-banana-pro | text → image | 40¢ | |
nano-banana-pro--edit | image edit | 40¢ | |
ideogram--custom-models--generate | Ideogram | text → image | 4¢ |
ideogram--object-removal | Ideogram | image edit | 4¢ |
ideogram--v3--generate-transparent | Ideogram | text → image | 4¢ |
ideogram--v4 | Ideogram | text → image | ~0.9¢/MP |
ideogram--v4--fast | Ideogram | text → image | ~0.63¢/MP |
ideogram--v4--image-to-image | Ideogram | image edit | ~0.9¢/MP |
ideogram--v4--image-to-image--lora | Ideogram | image edit | ~1.35¢/MP |
ideogram--v4--instant | Ideogram | text → image | ~0.9¢/MP |
ideogram--v4--lora | Ideogram | text → image | ~1.35¢/MP |
ideogram--v4--tiling | Ideogram | text → image | ~3.6¢/MP |
ideogram--v4--tiling--lora | Ideogram | text → image | ~4.05¢/MP |
image-background-removal | Ideogram | image edit | 6¢ |
luma--uni-1--v1--edit | Luma AI | image edit | 6¢ |
luma--uni-1--v1--max | Luma AI | text → image | 14¢ |
luma--uni-1--v1--max--edit | Luma AI | image edit | 14¢ |
luma--uni-1--v1--text-to-image | Luma AI | text → image | 6¢ |
gpt-image-2 | OpenAI | text → image | 29¢ |
gpt-image-2--edit | OpenAI | image edit | 29¢ |
gpt-image-2-5--flare--edit | OpenAI | image edit | 13¢ |
gpt-image-2-5--flare--text-to-image | OpenAI | text → image | 12¢ |
gpt-image-2-5--sunburst--edit | OpenAI | image edit | 13¢ |
gpt-image-2-5--sunburst--text-to-image | OpenAI | text → image | 12¢ |
alibaba--qwen-image-3--edit | Qwen | image edit | 5¢ |
alibaba--qwen-image-3--text-to-image | Qwen | text → image | 5¢ |
recraft--v4--style--pro--text-to-image | Recraft | text → image | 12¢ |
recraft--v4--style--pro--text-to-vector | Recraft | text → image | 15¢ |
recraft--v4--style--text-to-image | Recraft | text → image | 5¢ |
recraft--v4--style--text-to-vector | Recraft | text → image | 6¢ |
Video
| model | Owner | Type | Price |
|---|---|---|---|
alibaba--happy-horse--image-to-video | Alibaba | image → video | ~16.8¢/s |
alibaba--happy-horse--reference-to-video | Alibaba | reference → video | ~16.8¢/s |
alibaba--happy-horse--text-to-video | Alibaba | text → video | ~16.8¢/s |
alibaba--happy-horse--v1-1--image-to-video | Alibaba | image → video | ~16.8¢/s |
alibaba--happy-horse--v1-1--reference-to-video | Alibaba | reference → video | ~16.8¢/s |
alibaba--happy-horse--v1-1--text-to-video | Alibaba | text → video | ~16.8¢/s |
alibaba--happy-horse--video-edit | Alibaba | text → video | ~33.6¢/s |
alibaba--wan-3-0--image-to-video | Alibaba | image → video | ~12¢/s |
alibaba--wan-3-0--reference-to-video | Alibaba | reference → video | ~12¢/s |
alibaba--wan-3-0--text-to-video | Alibaba | text → video | ~12¢/s |
alibaba--wan-3-0-prime--image-to-video | Alibaba | image → video | ~16.8¢/s |
alibaba--wan-3-0-prime--reference-to-video | Alibaba | reference → video | ~16.8¢/s |
alibaba--wan-3-0-prime--text-to-video | Alibaba | text → video | ~16.8¢/s |
wan--v2-7--edit-video | Alibaba | video edit | ~12¢/s |
wan--v2-7--image-to-video | Alibaba | image → video | ~12¢/s |
wan--v2-7--reference-to-video | Alibaba | reference → video | ~12¢/s |
wan--v2-7--text-to-video | Alibaba | text → video | ~12¢/s |
blackforestlabs--flux-3--draft-enhance | Black Forest Labs | text → video | ~34.8¢/s |
blackforestlabs--flux-3--edit-video | Black Forest Labs | video edit | ~3.6¢/s |
blackforestlabs--flux-3--extend-video | Black Forest Labs | video edit | ~49.2¢/s |
blackforestlabs--flux-3--extend-video--draft | Black Forest Labs | video edit | ~14.4¢/s |
blackforestlabs--flux-3--first-last-frame-to-video | Black Forest Labs | text → video | ~20.4¢/s |
blackforestlabs--flux-3--first-last-frame-to-video--draft | Black Forest Labs | text → video | ~7.2¢/s |
blackforestlabs--flux-3--image-to-video | Black Forest Labs | image → video | ~20.4¢/s |
blackforestlabs--flux-3--image-to-video--draft | Black Forest Labs | image → video | ~7.2¢/s |
blackforestlabs--flux-3--keyframes-to-video | Black Forest Labs | text → video | ~20.4¢/s |
blackforestlabs--flux-3--keyframes-to-video--draft | Black Forest Labs | text → video | ~7.2¢/s |
blackforestlabs--flux-3--text-to-video | Black Forest Labs | text → video | ~20.4¢/s |
blackforestlabs--flux-3--text-to-video--draft | Black Forest Labs | text → video | ~7.2¢/s |
blackforestlabs--flux-video-upscale | Black Forest Labs | video edit | ~16.8¢/s |
bytedance--seedance-2-0--mini--image-to-video | ByteDance | image → video | ~18.56¢/s |
bytedance--seedance-2-0--mini--reference-to-video | ByteDance | reference → video | ~18.56¢/s |
bytedance--seedance-2-0--mini--text-to-video | ByteDance | text → video | ~18.56¢/s |
bytedance--seedance-2-5--image-to-video | ByteDance | image → video | ~56.76¢/s |
bytedance--seedance-2-5--reference-to-video | ByteDance | reference → video | ~56.76¢/s |
bytedance--seedance-2-5--text-to-video | ByteDance | text → video | ~56.76¢/s |
seedance-2-0--fast--image-to-video | ByteDance | image → video | $1.62 |
seedance-2-0--fast--reference-to-video | ByteDance | reference → video | $1.61 |
seedance-2-0--fast--text-to-video | ByteDance | text → video | $4.80 |
seedance-2-0--image-to-video | ByteDance | image → video | $4.04 |
seedance-2-0--reference-to-video | ByteDance | reference → video | $8.13 |
seedance-2-0--text-to-video | ByteDance | text → video | $6.00 |
google--gemini-omni-flash--v1-1--edit | text → video | ~12¢/s | |
google--gemini-omni-flash--v1-1--image-to-video | image → video | ~12¢/s | |
google--gemini-omni-flash--v1-1--text-to-video | text → video | ~12¢/s | |
veo3-1--fast--reference-to-video | reference → video | ~18¢/s | |
veo3-1--lite | text → video | ~6¢/s | |
veo3-1--lite--first-last-frame-to-video | text → video | ~6¢/s | |
veo3-1--lite--image-to-video | image → video | ~6¢/s | |
kling-video--o3--4k--image-to-video | Kling | image → video | ~50.4¢/s |
kling-video--o3--4k--reference-to-video | Kling | reference → video | ~50.4¢/s |
kling-video--o3--4k--text-to-video | Kling | text → video | ~50.4¢/s |
kling-video--o3--4k--video-to-video--edit | Kling | text → video | ~50.4¢/s |
kling-video--o3--4k--video-to-video--reference | Kling | text → video | ~50.4¢/s |
kling-video--v3--4k--image-to-video | Kling | image → video | ~50.4¢/s |
kling-video--v3--4k--text-to-video | Kling | text → video | ~50.4¢/s |
kling-video--v3--pro--image-to-video | Kling | image → video | $2.22 |
kling-video--v3--pro--text-to-video | Kling | text → video | $2.22 |
kling-video--v3--standard--image-to-video | Kling | image → video | $2.50 |
kling-video--v3--standard--text-to-video | Kling | text → video | $2.50 |
kling-video--v3--turbo--pro--image-to-video | Kling | image → video | ~16.8¢/s |
kling-video--v3--turbo--pro--text-to-video | Kling | text → video | ~16.8¢/s |
kling-video--v3--turbo--standard--image-to-video | Kling | image → video | ~13.44¢/s |
kling-video--v3--turbo--standard--text-to-video | Kling | text → video | ~13.44¢/s |
lightricks--ltx-2-5--audio-to-video--fast | Lightricks | audio → video | ~15.6¢/s |
lightricks--ltx-2-5--audio-to-video--pro | Lightricks | audio → video | ~20.4¢/s |
lightricks--ltx-2-5--image-to-video--fast | Lightricks | image → video | ~10.8¢/s |
lightricks--ltx-2-5--image-to-video--pro | Lightricks | image → video | ~14.4¢/s |
lightricks--ltx-2-5--text-to-video--fast | Lightricks | text → video | ~10.8¢/s |
lightricks--ltx-2-5--text-to-video--pro | Lightricks | text → video | ~14.4¢/s |
ltx-2-3--reframe | Lightricks | video edit | ~12¢/s |
ltx-2-3-22b--audio-to-video | Lightricks | audio → video | ~0.19¢/MP |
ltx-2-3-22b--audio-to-video--lora | Lightricks | audio → video | ~0.22¢/MP |
ltx-2-3-22b--distilled--audio-to-video | Lightricks | audio → video | ~0.14¢/MP |
ltx-2-3-22b--distilled--audio-to-video--lora | Lightricks | audio → video | ~0.17¢/MP |
ltx-2-3-22b--distilled--image-to-video | Lightricks | image → video | ~0.14¢/MP |
ltx-2-3-22b--distilled--image-to-video--lora | Lightricks | image → video | ~0.17¢/MP |
ltx-2-3-22b--distilled--reference-video-to-video | Lightricks | text → video | ~0.14¢/MP |
ltx-2-3-22b--distilled--reference-video-to-video--lora | Lightricks | text → video | ~0.17¢/MP |
ltx-2-3-22b--distilled--text-to-video | Lightricks | text → video | ~0.14¢/MP |
ltx-2-3-22b--distilled--text-to-video--lora | Lightricks | text → video | ~0.17¢/MP |
ltx-2-3-22b--distilled--video-to-video | Lightricks | text → video | ~0.14¢/MP |
ltx-2-3-22b--distilled--video-to-video--lora | Lightricks | text → video | ~0.17¢/MP |
ltx-2-3-22b--extend-video | Lightricks | video edit | ~0.19¢/MP |
ltx-2-3-22b--extend-video--lora | Lightricks | video edit | ~0.22¢/MP |
ltx-2-3-22b--image-to-video | Lightricks | image → video | ~0.19¢/MP |
ltx-2-3-22b--image-to-video--lora | Lightricks | image → video | ~0.22¢/MP |
ltx-2-3-22b--reference-video-to-video | Lightricks | text → video | ~0.19¢/MP |
ltx-2-3-22b--reference-video-to-video--lora | Lightricks | text → video | ~0.22¢/MP |
ltx-2-3-22b--text-to-video | Lightricks | text → video | ~0.19¢/MP |
ltx-2-3-22b--text-to-video--lora | Lightricks | text → video | ~0.22¢/MP |
ltx-2-3-22b--video-to-video | Lightricks | text → video | ~0.19¢/MP |
ltx-2-3-22b--video-to-video--lora | Lightricks | text → video | ~0.22¢/MP |
ltx-2-3-quality--audio-to-video | Lightricks | audio → video | ~0.29¢/MP |
ltx-2-3-quality--audio-to-video--lora | Lightricks | audio → video | ~0.32¢/MP |
ltx-2-3-quality--clean-plate | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--cross-eyed | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--day-to-night | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--deblur | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--decompression | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--extend-video | Lightricks | video edit | ~0.29¢/MP |
ltx-2-3-quality--extend-video--lora | Lightricks | video edit | ~0.29¢/MP |
ltx-2-3-quality--hdr | Lightricks | text → video | ~0.32¢/MP |
ltx-2-3-quality--hdr--lora | Lightricks | text → video | ~0.32¢/MP |
ltx-2-3-quality--image-to-video | Lightricks | image → video | ~0.29¢/MP |
ltx-2-3-quality--image-to-video--lora | Lightricks | image → video | ~0.32¢/MP |
ltx-2-3-quality--ingredient | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--instant-shave | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--outpaint | Lightricks | video edit | ~0.29¢/MP |
ltx-2-3-quality--outpaint--lora | Lightricks | video edit | ~0.29¢/MP |
ltx-2-3-quality--reference-video-to-video | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--reference-video-to-video--lora | Lightricks | text → video | ~0.32¢/MP |
ltx-2-3-quality--render-to-real | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--text-to-video | Lightricks | text → video | ~0.29¢/MP |
ltx-2-3-quality--text-to-video--lora | Lightricks | text → video | ~0.32¢/MP |
ltx-2-3-quality--water-simulation | Lightricks | text → video | ~0.29¢/MP |
luma--ray--v3-2--image-to-video | Luma AI | image → video | ~7.2¢/s |
luma--ray--v3-2--reframe | Luma AI | video edit | ~14.4¢/s |
luma--ray--v3-2--text-to-video | Luma AI | text → video | ~24¢/s |
luma--ray--v3-2--video-to-video | Luma AI | text → video | ~25.92¢/s |
minimax-h3--image-to-video | MiniMax | image → video | up to $4.68 (per second) |
minimax-h3--reference-to-video | MiniMax | reference → video | up to $4.68 (per second) |
minimax-h3--text-to-video | MiniMax | text → video | up to $4.68 (per second) |
sync-lipsync--v2 | Sync | video edit | $6.00 |
video-background-removal | VEED | video edit | 24¢ |
video-subtitles | VEED | video edit | 96¢ |
Speech & music
| model | Owner | Type | Price |
|---|---|---|---|
seed-speech--tts--v2 | ByteDance | text → speech | ~4¢ / 1k chars |
elevenlabs--tts--turbo-v2-5 | ElevenLabs | text → speech | ~6¢ / 1k chars |
minimax-music--v2-6 | MiniMax | music | 18¢ |
Call it
In a connected MCP client, pass the service, action, and inputs to use:
{
"service": "fal",
"action": "generate",
"params": {
"model": "nano-banana-pro--edit"
},
"max_cost_cents": 100
}
Or over HTTP with a Vaaya API key:
curl -X POST https://vaaya.ai/api/run/fal/generate \
-H "Authorization: Bearer $VAAYA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"nano-banana-pro--edit","max_cost_cents":100}'
Service details
fal/generate
varies by params. Provider errors are not charged.
Vaaya calls the provider with its own account and bills you the catalog price.
Held server-side by Vaaya; your agent never receives a fal key.
More from fal
Try this action.
Use the example above in your application, or connect an agent and describe the task. Charges appear in your Vaaya account.
npx @vaaya/mcp install