Available Floyo Partner Nodes

pricing note some node costs are calculated dynamically based on input factors such as resolution, duration, and fps the final cost of a generation may vary accordingly refer to each node's pricing details for specifics image generation nodes black forest labs (flux) flux dev use the open weight flux development model for image generation $0 025/megapixel flux pro 1 1 generate images with improved prompt adherence using flux pro 1 1 $0 04/megapixel flux pro 1 fill inpaint and outpaint images using flux pro $0 05/megapixel flux ultra generate high resolution 4mp images with optional raw mode for natural aesthetics $0 06/image flux pro kontext context aware image to image generation with character consistency $0 04/image flux pro kontext max maximum quality context aware generation with advanced typography $0 08/image flux pro kontext max text to image text to image with aspect ratio controls and max quality toggle $0 08/image flux pro kontext multi compose 2 4 images together with context awareness $0 04/image · $0 08/image (max quality) flux 2 pro text to image generate images using the next generation 32b flux 2 pro model $0 03/mp first, then $0 015/mp flux 2 pro image edit edit images using flux 2 pro with text prompts $0 03/mp first + $0 015/mp subsequent · reference $0 015/mp flux 2 \[flex] generate images with full control over steps and guidance parameters $0 05/megapixel + $0 05/megapixel per reference image flux schnell fast image generation with flux schnell $0 003/megapixel flux general use controlnets, ip adapters, and loras with flux dev $0 075/megapixel alibaba alibaba wan 2 6 text to image generate images using alibaba's wan 2 6 model $0 04/image alibaba wan 2 7 image pro unified generate and edit images using alibaba's wan 2 7 image pro with unified architecture $0 075/image alibaba wan 2 7 image unified generate and edit images using alibaba's wan 2 7 image unified architecture $0 03/image qwen image edit edit images using qwen with precise text and semantic editing $0 03/megapixel qwen image edit plus lora edit images using qwen with integrated lora capabilities $0 035/megapixel qwen image max text to image generate images using qwen image max $0 075/image qwen image max image to edit edit images using qwen image max's advanced editing capabilities $0 075/image qwen image 2 pro unified generate and edit images using qwen image 2 pro with support for up to 3 input images $0 075/image bytedance seedream 4 0 unified generate and edit images using seedream 4 0's unified architecture $0 03/image seedream 4 5 unified generate and edit images using seedream 4 5's unified architecture $0 04/image dreamina v3 1 text to image generate cinematic quality images using dreamina v3 1 $0 03/image seedream 5 0 lite unified generate, edit, and blend images using seedream 5 0 lite with support for up to 14 input images $0 035/image google imagen4 preview generate images using google's imagen 4 preview model $0 04/image nano banana text to image generate images using gemini's native image generation $0 039/image nano banana edit edit images using gemini's native editing capabilities $0 039/image nano banana pro unified generate and edit images using nano banana pro (gemini 3 pro image) $0 15/image · $0 30/image (4k) nano banana 2 unified generate and edit images using nano banana 2 (gemini 2) with web search support and up to 14 input images $0 08 (1k), $0 12 (2k), $0 16 (4k)/image , web search option adds $0 008 per request tencent hunyuan image v3 text to image generate images using tencent's hunyuan image v3 $0 10/megapixel hunyuan image v3 instruct text to image generate images using hunyuan image v3 with instruction following capabilities $0 09/megapixel hunyuan image v3 instruct edit edit images using hunyuan image v3's instruction based editing $0 09/megapixel openai gpt image 2 0 text to image generate images using openai's gpt image 2 0 model low $0 06 $0 07/image · medium $0 09 $0 16/image · high $0 21 $0 46/image (varies by resolution) gpt image 2 0 edit edit images using openai's gpt image 2 0 model low $0 11 $0 12/image · medium $0 14 $0 21/image · high $0 26 $0 51/image (varies by resolution) gpt image 1 5 text to image generate images using openai's gpt image 1 5 model low $0 009 $0 013/image · medium $0 034 $0 051/image · high $0 133 $0 200/image gpt image 1 5 edit edit images using openai's gpt image 1 5 model low $0 009 $0 013/image · medium $0 034 $0 051/image · high $0 133 $0 200/image kling kling o1 image edit edit images using kling's o1 image editing model $0 028/image xai grok imagine image generate images using xai's grok imagine model $0 02/image grok imagine image edit edit images using grok imagine $0 022/image other image models ideogramv3 generate images with industry leading typography and text rendering $0 03/image (turbo) · $0 06/image (default) · $0 09/image (quality) hidreamfull generate images using hidream's 17b parameter open source model $0 05/megapixel recraft v3 professional design generation with vector support and text positioning $0 04/image · $0 08/image (vector style) recraft v3 image to image transform images using recraft v3 with style and strength controls $0 04/image · $0 08/image (vector style) recraft v3 create style create custom recraft styles from reference images for use in generation $0 04/training sana fast high resolution image generation up to 4k using nvidia's efficient model $0 001/megapixel reve text to image generate images using reve's high fidelity image model $0 04/image video generation nodes alibaba wan alibaba wan 2 5 image to video generate videos from images using wan 2 5 $0 05/sec (480p) · $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 5 text to video generate videos from text using wan 2 5 $0 05/sec (480p) · $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 6 image to video generate videos from images using wan 2 6 $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 6 text to video generate videos from text using wan 2 6 $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 6 reference to video generate videos with reference image guidance using wan 2 6 $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 7 image to video generate videos from images using wan 2 7 $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 7 text to video generate videos from text using wan 2 7 $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 7 reference to video generate videos with reference image guidance using wan 2 7 $0 10/sec (720p) · $0 15/sec (1080p) alibaba wan 2 7 video editing edit existing videos using wan 2 7 $0 10/sec (720p) · $0 15/sec (1080p) wan pro image to video generate videos from images using wan pro $0 80/5s alibaba happy horse happy horse 1 0 text to video generate videos from text using happy horse 1 0 $0 14/sec (720p) · $0 24/sec (1080p) happy horse 1 0 image to video generate videos from images using happy horse 1 0 $0 14/sec (720p) · $0 24/sec (1080p) happy horse 1 0 reference to video generate videos with reference image guidance using happy horse 1 0 $0 14/sec (720p) · $0 24/sec (1080p) happy horse 1 0 video editing edit existing videos using happy horse 1 0 $0 14/sec (720p) · $0 24/sec (1080p) · total price depends on input video duration bytedance seedance seedance image to video generate videos from images using seedance $0 018/sec (480p) · $0 039/sec (720p) · $0 088/sec (1080p) seedance text to video generate videos from text using seedance $0 018/sec (480p) · $0 039/sec (720p) · $0 088/sec (1080p) seedance pro image to video generate videos from images using seedance pro $0 025/sec (480p) · $0 054/sec (720p) · $0 122/sec (1080p) seedance pro 1 5 video generate videos using seedance pro 1 5 480p $0 012/sec (no audio) · $0 024/sec (with audio) | 720p $0 026/sec (no audio) · $0 052/sec (with audio) | 1080p $0 058/sec (no audio) · $0 116/sec (with audio) seedance 2 0 text to video generate videos from text using seedance 2 0 $0 11/sec (480p) · $0 24/sec (720p) · $0 54/sec (1080p) seedance 2 0 fast text to video fast video generation from text using seedance 2 0 $0 09/sec (480p) · $0 19/sec (720p) seedance 2 0 image to video generate videos from images using seedance 2 0 $0 11/sec (480p) · $0 24/sec (720p) · $0 54/sec (1080p) seedance 2 0 fast image to video fast video generation from images using seedance 2 0 $0 09/sec (480p) · $0 19/sec (720p) seedance 2 0 reference to video generate videos with reference guidance using seedance 2 0 $0 11/sec (480p) · $0 24/sec (720p) · $0 54/sec (1080p) · with video input $0 15/sec (720p) · $0 33/sec (1080p) seedance 2 0 fast reference to video fast video generation with reference guidance using seedance 2 0 $0 09/sec (480p) · $0 19/sec (720p) · with video input $0 12/sec (720p) omnihuman video generation generate avatar videos with audio using omnihuman $0 12/sec · total price depends on audio duration kling kling video generation generate videos using kling's standard model $0 045/sec kling pro v1 6 video generation generate videos using kling pro v1 6 $0 098/sec kling master v2 0 video generation generate videos using kling master v2 0 $1 40/5s · $0 28/additional sec kling v2 1 pro image to video generate videos from images using kling v2 1 pro $0 49/5s · $0 098/additional sec kling v2 5 turbo pro image to video fast video generation from images using kling v2 5 turbo $0 35/5s · $0 07/additional sec kling v2 6 pro image to video generate videos from images using kling v2 6 pro $0 07/sec (no audio) · $0 14/sec (with audio) · $0 168/sec (voice clone) kling v2 6 standard motion control generate videos with motion control using kling v2 6 $0 07/sec · total price depends on input video duration and resolution kling o3 standard image to video generate videos from images using kling o3 standard $0 168/sec (no audio) · $0 224/sec (with audio) kling o3 standard reference to video generate videos with reference guidance using kling o3 standard $0 084/sec (no audio) · $0 112/sec (with audio) kling o3 pro image to video generate videos from images using kling o3 pro $0 224/sec (no audio) · $0 28/sec (with audio) kling o3 pro reference to video generate videos with reference guidance using kling o3 pro $0 112/sec (no audio) · $0 14/sec (with audio) kling o3 pro text to video generate videos from text using kling o3 pro $0 224/sec (no audio) · $0 28/sec (with audio) kling o3 pro video to video edit edit videos using kling o3 pro with reference image and element support $0 168/sec · total price depends on input video duration and resolution kling o3 standard video to video edit edit videos using kling o3 standard with reference image and element support $0 126/sec · total price depends on input video duration and resolution kling o3 pro video to video reference transform videos with reference guidance using kling o3 pro $0 168/sec kling o3 standard video to video reference transform videos with reference guidance using kling o3 standard $0 126/sec kling v3 standard image to video generate videos from images using kling v3 standard $0 168/sec (no audio) · $0 252/sec (with audio) · +$0 308 (voice clone) kling v3 standard text to video generate videos from text using kling v3 standard $0 168/sec (no audio) · $0 252/sec (with audio) · +$0 308 (voice clone) kling v3 pro image to video generate videos from images using kling v3 pro $0 224/sec (no audio) · $0 336/sec (with audio) · +$0 392 (voice clone) kling v3 pro text to video generate videos from text using kling v3 pro $0 224/sec (no audio) · $0 336/sec (with audio) · +$0 392 (voice clone) kling v3 pro motion control generate videos with motion control using kling v3 pro with character orientation support $0 168/sec kling v3 standard motion control generate videos with motion control using kling v3 standard with character orientation support $0 126/sec kling omni image to video generate videos from images using kling omni $0 112/sec kling omni reference to video generate videos with reference guidance using kling omni $0 112/sec kling omni video to video edit edit videos using kling omni $0 168/sec · total price depends on input video duration and resolution kling omni video to video reference transform videos with reference guidance using kling omni $0 168/sec kling create voice create custom voice clones for use with kling video generation $0 035/run google veo google veo2 image to video generate videos from images using google veo 2 $0 50/sec veo3 video generation generate videos using google veo 3 $0 20/sec (no audio) · $0 40/sec (with audio) veo 3 1 first last frame to video generate videos from first and last frame using veo 3 1 $0 20/sec (no audio) · $0 40/sec (with audio) · $0 40/sec (4k, no audio) · $0 60/sec (4k, with audio) veo 3 1 fast first last frame to video fast video generation from first and last frame using veo 3 1 $0 10/sec (no audio) · $0 15/sec (with audio) · $0 30/sec (4k, no audio) · $0 35/sec (4k, with audio) minimax minimax video generation generate videos using minimax $0 50/video minimax text to video generate videos from text using minimax $0 50/video minimax subject reference generate videos with subject reference using minimax $0 50/video moonvalley moonvalley marey image to video generate videos from images using moonvalley marey $1 50/5s · $3 00/10s moonvalley marey text to video generate videos from text using moonvalley marey $1 50/5s · $3 00/10s moonvalley marey pose transfer transfer pose from a reference video to a subject using moonvalley marey $2 00/run moonvalley marey motion transfer transfer motion from a reference video to a subject using moonvalley marey $2 00/run pixverse pixverse c1 image to video generate videos from images using pixverse c1 $0 03 $0 12/sec depending on resolution · +audio adds $0 01 $0 025/sec pixverse c1 text to video generate videos from text using pixverse c1 $0 03 $0 12/sec depending on resolution · +audio adds $0 01 $0 025/sec pixverse c1 reference to video generate videos with reference guidance using pixverse c1 $0 03 $0 12/sec depending on resolution · +audio adds $0 01 $0 025/sec pixverse c1 transition generate transition videos between images using pixverse c1 $0 03 $0 12/sec depending on resolution · +audio adds $0 01 $0 025/sec pixverse swap swap faces or elements in videos using pixverse $0 15/5s (360p & 540p) · $0 20/5s (720p) · $0 40/5s (1080p) luma luma dream machine generate videos using luma dream machine $0 50/5s (540p) · $1 00/5s (720p) · $2 00/5s (1080p) · duration and resolution affect final cost openai sora 2 pro image to video generate videos from images using openai sora 2 pro $0 30/sec (720p) · $0 50/sec (1080p) lightricks ltx ltx 2 pro text to video generate videos from text using ltx 2 pro $0 06/sec (1080p) · $0 12/sec (1440p) · $0 24/sec (2160p) ltx 2 pro image to video generate videos from images using ltx 2 pro $0 06/sec (1080p) · $0 12/sec (1440p) · $0 24/sec (2160p) ltx 2 fast text to video fast video generation from text using ltx 2 $0 04/sec (1080p) · $0 08/sec (1440p) · $0 16/sec (2160p) ltx 2 fast image to video fast video generation from images using ltx 2 $0 04/sec (1080p) · $0 08/sec (1440p) · $0 16/sec (2160p) ltx 2 retake video regenerate or modify videos using ltx 2 $0 10/sec ltx 2 3 pro text to video generate videos from text using ltx 2 3 pro with audio support $0 06/sec (1080p) · $0 12/sec (1440p) · $0 24/sec (2160p) ltx 2 3 pro image to video generate videos from images using ltx 2 3 pro with end image and audio support $0 06/sec (1080p) · $0 12/sec (1440p) · $0 24/sec (2160p) ltx 2 3 fast text to video fast video generation from text using ltx 2 3 with up to 20s duration $0 04/sec (1080p) · $0 08/sec (1440p) · $0 16/sec (2160p) ltx 2 3 fast image to video fast video generation from images using ltx 2 3 with up to 20s duration $0 04/sec (1080p) · $0 08/sec (1440p) · $0 16/sec (2160p) ltx 2 3 audio to video generate videos from audio input using ltx 2 3 with optional image guidance $0 10/sec ltx 2 3 extend video extend existing videos from the start or end using ltx 2 3 $0 10/sec ltx 2 3 retake video retake or modify video segments with audio/video replacement using ltx 2 3 $0 10/sec lightx lightx relight relight videos with ai powered lighting adjustments $0 10/sec lightx recamera change camera angles and perspectives in videos $0 10/sec xai grok imagine video text to video generate videos from text using xai's grok imagine $0 05/sec (480p) · $0 07/sec (720p+) grok imagine video image to video generate videos from images using xai's grok imagine $0 05/sec + $0 002/image input grok imagine video edit edit videos using xai's grok imagine with prompt guided transformations $0 06/output sec (480p) · $0 08/output sec (720p+) · total price depends on input video duration grok imagine reference to video generate videos with reference image guidance using grok imagine $0 05/sec (480p) · $0 07/sec (720p+) + $0 002/image input grok imagine extend video extend existing videos using grok imagine $0 06/sec (480p) · $0 08/sec (720p+) vidu vidu q3 text to video generate videos from text using vidu q3 $0 07/sec (360p/540p) · $0 154/sec (720p/1080p) vidu q3 image to video generate videos from images using vidu q3 $0 07/sec (360p/540p) · $0 154/sec (720p/1080p) other video models infinity star text to video generate videos from text using infinity star $0 07/video krea wan 14b video to video transform videos using krea wan 14b $0 025/sec · total price depends on input video duration and resolution 3d generation nodes hyper3d hyper3d rodin v2 generate 3d models using hyper3d rodin v2 $0 40/gen · $1 20/gen (highpack) tripo tripo3d image to 3d generate 3d models from single images $0 20 (no textures) · $0 30 (standard textures) · $0 40 (hd textures) · +$0 05 (quad remesh) tripo3d multiview to 3d generate 3d models from multiple view images $0 20 (no textures) · $0 30 (standard textures) · $0 40 (hd textures) · +$0 05 (quad remesh) meshy meshy 6 image to 3d generate 3d models from images using meshy v6 $0 80/gen meshy 6 text to 3d generate 3d models from text using meshy v6 $0 80/gen tencent hunyuan 3d v3 1 pro image to 3d generate 3d models from images using hunyuan 3d v3 1 pro $0 375/gen · +$0 15 (pbr materials) · +$0 15 (multiview) · +$0 15 (custom face count) hunyuan 3d v3 1 pro text to 3d generate 3d models from text using hunyuan 3d v3 1 pro $0 375/gen · +$0 15 (pbr materials) · +$0 15 (custom face count) language models (llms) llm generate text using leading language models via openrouter pricing varies by model minimax/minimax m2 5 stepfun/step 3 5 flash deepseek/deepseek v3 2 google/gemini 3 flash preview anthropic/claude sonnet 4 6 anthropic/claude opus 4 6 openrouter/hunter alpha google/gemini 2 5 flash moonshotai/kimi k2 5 x ai/grok 4 1 fast google/gemini 2 5 flash lite arcee ai/trinity large preview openai/gpt oss 120b anthropic/claude sonnet 4 5 xiaomi/mimo v2 flash z ai/glm 5 openai/gpt 5 nano google/gemini 3 1 pro preview anthropic/claude haiku 4 5 openai/gpt 4 1 meta llama/llama 4 maverick custom (specify any openrouter model) qwen 3 5 plus multimodal text generation using alibaba's qwen 3 5 plus with image and video understanding $0 40/1m input tokens, $2 40/1m output tokens · pricing varies by usage vision language models (vlms) vlm analyze images and generate text using vision language models pricing varies by model google/gemini 2 5 flash anthropic/claude sonnet 4 5 openai/gpt 4o qwen/qwen3 vl 235b a22b instruct x ai/grok 4 fast custom (specify any openrouter model) audio, speech & music nodes elevenlabs elevenlabs tts generate speech from text using elevenlabs $0 10/1k characters minimax minimax speech 2 8 hd generate speech from text using minimax speech 2 8 hd $0 10/1k characters minimax music 2 6 generate music tracks using minimax music 2 6 $0 15/run fish audio fish audio tts generate high quality speech from text with preset voices and prosody controls $15 00 / m utf 8 bytes (est $0 015/1k characters) fish audio tts advanced full control text to speech with model selection, sampling parameters, and audio format settings $15 00 / m utf 8 bytes (est $0 015/1k characters) fish audio create voice model create custom voice models from audio samples for use with fish audio tts free lip sync nodes kling kling ai avatar v2 pro lip sync \[image to video] generate lip synced avatar videos from images using kling ai avatar v2 pro $0 115/sec latentsync latentsync lip sync synchronize lip movements to audio using latentsync $0 20 base (up to 40s) · $0 005/additional sec sync so sync lipsync synchronize lip movements to audio using sync so lipsync 2 $0 05/sec · lipsync 2 pro $0 083/sec · react 1 $0 167/sec upscaling nodes clarity ai clarity upscaler upscale and enhance images using clarity ai $0 03/megapixel · total price depends on input image resolution bytedance seedvr upscaler upscale images using seedvr2 with one step processing $0 001/megapixel · total price depends on input resolution seedvr video upscaler upscale videos using seedvr2 with multiple output format and quality options $0 001/megapixel (video width×height×frames) · ≈$0 25 for 1920×1080×121 · total price depends on input resolution and duration other upscalers video upscaler general purpose video upscaling with configurable scale factor $0 001/megapixel · total price depends on input resolution and duration topaz labs topaz video upscale + frame interpolation upscale videos and interpolate frames using topaz $0 013/sec (1080p, 24fps) · $0 053/sec (4k, 24fps) · min $0 50 · frame interpolation increases cost proportionally training nodes black forest labs flux lora trainer train custom loras for flux models $0 002/step (default 1000 steps = $2/run) lightricks ltx 2 video lora trainer train custom lora adapters for ltx 2 video models with optional audio support $0 0048/step more floyo partner nodes are coming if there are any specific apis out there you need for a workflow we can quickly create a custom node and add new api support for it just let us know at support\@floyo ai mailto\ support\@floyo ai