| Model | Use for | Modalities | Credits |
|---|---|---|---|
| Runway — Video Generation | |||
RunwayGen-4.5Latest | Most advanced video generation with high realism and cinematography | Text to VideoImage to Video | 12/sec |
RunwayGen-4 Aleph | Video editing and stylization | Video to Video edits | 15/sec |
RunwayGen-4 Video | General-purpose video generation | Image to Video | 12/sec |
RunwayGen-4 Video Turbo | Budget-friendly video generation | Image to Video | 5/sec |
RunwayAct-Two | Character animation with a performance video (3 sec min) | Character performance | 5/sec |
RunwayAleph 2.0Latest | Video editing and stylization | Video to Video edits | 28/sec |
RunwayRubyLatest | Convert any SDR video into professional-grade HDR | Video to Video | 20/sec |
RunwayEnhance Frame Rate | converts any video to the frame rate your delivery pipeline requires | Video to Video | 1/ 2 sec |
| Runway — Image Generation | |||
RunwayGen-4 Image | Most advanced image generation and editing | Text to ImageImage to Image | 720p5/img1080p8/img |
RunwayGen-4 Image Turbo | Budget-friendly image generation | Image to Image | 2/img |
| Runway — Post-processing Generation | |||
RunwayStitch video | Combine multiple videos into a single clip | Workflows | 1/20 seconds |
RunwayAdd audio | Add generated or uploaded audio to a video in Workflows | Workflows | 1/20 seconds |
RunwayExtract audio | Extract audio from an uploaded or generated video | Workflows | 1/20 seconds |
| Runway — Live video Generation | |||
RunwayCharacters | Real-time conversational AI avatars | Live Avatar | 2/6 sec |
| Alibaba — Video Generation | |||
AlibabaWAN2.6 | Video generation with or without audio | Text to VideoImage to Video | 720p10/sec1080p15/sec |
AlibabaWAN2.6 Flash | Video generation with or without audio | Text to VideoImage to Video | 720p5/sec1080p10/sec |
AlibabaHappyHorse 1.0 | General-purpose video generation | Text to VideoImage to Video | 1080p30/sec72015/sec |
AlibabaWan 3.0 | Budget-friendly video with audio | Text to VideoImage to VideoVideo to Video | 480p5/sec720p10/sec1080p20/sec |
| ByteDance — Image Generation | |||
ByteDanceSeedream 5.0-lite | Budget-friendly image generation | Text to Image | 2K/3K4/img |
ByteDanceSeedream 5.0 Pro | Precision image generation and editing | Text to ImageImage to Image | 1K5/img2K10/img |
ByteDanceSeedream 5.0 Pro Layers | Split any image into layers for editing | Image to Layers | 18/run |
ByteDanceSeedream 5.0 Flash | Fast, budget-friendly image generation with up to 10 reference images | Text to ImageImage to Image | 2img |
ByteDanceSeedream 5.0 Flash Layers | Budget-friendly way to split any image into layers for editing | Image to Layers | 4/img |
| ByteDance — Video Generation | |||
ByteDanceSeedance 2.0 | Multi-modal video generation with audio | Text to VideoImage to VideoVideo to Video | 480p36/sec720p36/sec1080p40/sec4K150/sec |
ByteDanceSeedance 2.0 Fast | Multi-modal video generation with audio, built for speed and exploration | Text to VideoImage to VideoVideo to Video | 29/sec |
ByteDanceSeedance 2.0 Mini | Budget friendly video generation, built for speed and exploration | Text to VideoImage to VideoVideo to Video | 16/sec |
ByteDanceSeedance 2.5 | Continuous, high-fidelity audio-video clips with up to 50 multimodal reference | Text to Video Image to VideoVideo to Video | 72030/sec + 34 (1080p), 15 (720p), 10 (480p) per sec of input video48020/sec + 34 (1080p), 15 (720p), 10 (480p) per sec of input video1080p68/sec + 34 (1080p), 15 (720p), 10 (480p) per sec of input video |
| ByteDance — Audio Generation | |||
ByteDanceSeed Audio 1.0 | Generate multi-character dialogue, music, and ambient sound simultaneously | Text to AudioAudio to Audio | 15/min (5 credit minimum per generation) |
| Google — Video Generation | |||
GoogleVeo 3.1 | Most advanced video generation with audio and speech | Text to VideoImage to VideoStart/End Frame | No audio20/secWith audio40/sec |
GoogleGemini Omni Flash | Video editing and multi-modal generation | Image to VideoVideo to VideoText to Video | 10/sec + 1 per additional reference or /sec of input video |
| Google — Image Generation | |||
GoogleNano Banana Pro 2 | Most advanced and budget-friendly image generation | Text to ImageImage to Image | 1K7/img2K11/img4K16/img |
GoogleNano Banana Pro | Most advanced image generation and editing | Text to ImageImage to Image | 1K/2K20/img4K40/img |
GoogleNano Banana | Budget-friendly image generation and editing | Text to ImageImage to Image | 5/img |
GoogleNano Banana Pro 2 Lite | Fast and budget-friendly image generation | Text to ImageImage to Image | 4/img |
GoogleNano Banana 2.1 | Advanced image generation and editing | Text to ImageImage to Image | 1K4/img2K6/img4K12/img |
| Google — LLM Generation | |||
GoogleGemini Flash 2.5 | Well-rounded and budget-friendly LLM for text processing, image analysis, and more in Workflows. | Text ProcessingImage analysis | 1/run |
| Google — Audio Generation | |||
GoogleLyria 3 Pro | Generating music in Workflows | Text to Audio | 8/song |
GoogleLyria 3 Clip | Generating music in Workflows | Text to Audio | 4/song |
GoogleGemini 3.8 Flash TTS | Expressive text-to-speech for voiceovers and narration | Text to Speech | 7/4000 characters |
GoogleGemini 3.8 Flash-Lite TTS | Budget-friendly, faster text-to-speech for narration and multilingual content | Text to Speech | 4/4000 characters |
| Kling — Video Generation | |||
KlingKling 3.0 Pro | Most advanced video generation with audio and speech | Image to VideoText to VideoStart/End FrameMultishot | No audio12/secWith audio17/sec |
KlingKling 3.0 Std | Budget-friendly video generation | Image to VideoText to VideoStart/End Frame | No audio9/secWith audio13/sec |
KlingKling 2.6 Pro | Previous-gen video generation with audio | Image to VideoText to VideoStart/End FrameAudio | 25/sec |
KlingKling 2.5 Turbo Pro | Previous-gen budget-friendly video generation | Start/End Frame | 720p12/sec1080p15/sec |
KlingKling 2.5 Turbo | Previous-gen budget-friendly video generation | Image to Video | 10/sec |
KlingKling 3.0 Motion Control | Character animation with a performance video | Character performance | 1080p17/sec720p13/sec |
KlingKling O3 | Multi-modal video generation with audio | Text to VideoImage to VideoKeyframesMulti-shot | 4K43/secPro17/secStandard13/sec |
KlingKling 3.0 Turbo | Budget friendly video generation built for speed and exploration | Text to VideoImage to Video | 720p14/sec1080p16/sec |
| Kling — Vidoe Generation | |||
KlingKling 4.0 | Long, continuous shots up to 30 seconds with keyframe control and multi-reference consistency | Text to VideoImage to VideoVideo to Video editsVideo to Video | 720p16/sec1080p24/sec |
| OpenAI — Image Generation | |||
OpenAIGPT Image 1.5 | Advanced image generation | Text to ImageImage to Image | 1024×102414/imgOther20/img |
OpenAIGPT Image 1 Mini | Budget-friendly image generation | Text to ImageImage to Image | 2/img |
OpenAIGPT Image 2 | Image generation with flexible balance of budget and quality | Text to ImageImage to Image | 1K & 2K (low quality)1/img1K & 2K (medium quality)5/img1K & 2K (high quality)20/img4K (low quality)2/img4K (medium quality)11/img4K (high quality)41/img |
OpenAIGPT Image 2.5 Flare | Fast image generation built for high volume and rapid iteration | Image to ImageText to ImageImage to Image | 1K16/img2K16/img4K19/img |
OpenAIGPT Image 2.5 Sunburst | High-fidelity precision-focused image generation | Text to ImageImage to Image | 1K16/img2K16/img4K19/img |
| OpenAI — LLM Generation | |||
OpenAIGPT-6 Astra | Advanced reasoning | Text processing | 40/run |
| Black Forest Labs — Image Generation | |||
Black Forest LabsFLUX.2 Max | Advanced image generation | Text to ImageImage to Image | 60010/img1K10/img2K13/img4K19/img |
Black Forest LabsFLUX.2 Klein | Budget-friendly image generation | Text to ImageImage to Image | 6004/img1K4/img2K5/img |
Black Forest LabsFLUX 3 Image | Advanced image generation and editing | Text to ImageImage to Image | 5126/img7686/img1K7/img2K14/img4K81/img |
| Black Forest Labs — Video Generation | |||
Black Forest LabsFLUX 3 | use for creating long, continuous single-take shots | Text to VideoImage to Video | 17/sec |
| Topaz AI — Upscale Generation | |||
Topaz AIUpscale to 4K | Upscaling video to 4K | Upscale video | 2/sec |
| Anthropic — LLM Generation | |||
AnthropicClaude | Well-rounded and budget-friendly LLM for text processing, image analysis, and more in Workflows. | Text processingImage analysis | Sonnet 4.53/runOpus 4.54/runOpus 4.84/runOpus 5.524/run |
| Magnific — Upscale Generation | |||
MagnificPrecision | Flexible, customizable image upscaling | Upscale | > 4k150/img≤ 4k25/img |
| Magnific — Image Generation | |||
MagnificStyle Transfer | Transform an image by applying various artistic styles | image to image | 15/img |
| xAI — Image Generation | |||
xAIGrok Imagine | Fast, budget-friendly image generation | Text to ImageImage to Image | 1K2/img2K7/img |
xAIGrok Image Quality | Realism and precision for text-heavy, detailed images | Text to ImageImage to Image | 1K7/img2K8/img |
xAIGrok Imagine Image 2.0 | Generating and editing images, with region edits and multi-image compositing | Text to ImageImage to Image | Low — 1K4/img + 1 per additional referenceLow — 2K6/img + 1 per additional referenceMedium — 1K6/img + 1 per additional referenceMedium — 2K8/img + 1 per additional reference |
| xAI — Video Generation | |||
xAIGrok Imagine | Fast, budget-friendly video generation with audio | Text to VideoImage to Video | 480p13/sec + 1 credit per reference frame720p17/sec + 1 credit per reference frame |
xAIGrok Imagine | fast, budget-friendly video editing and extending | Video to Video | 6/sec |
xAIGrok Imagine 1.5 | Fast, budget-friendly video generation with audio | Image to Video | 480p10/sec + 1 credit per reference frame720p16/sec + 1 credit per reference frame108029/sec + 1 credit per reference frame |
xAIGrok Imagine 1.5 Lite | Faster, lower-cost Grok video generation with native audio | Text to VideoImage to Video | 480p10/sec + 1 credit per reference frame72015/sec + 1 credit per reference frame108070/sec + 1 credit per reference frame |
| ElevenLabs — Audio Generation | |||
ElevenLabsText to Speech | Turn typed text into speech | Text to Audio | 1/50 characters |
ElevenLabsText to SFX | Turn typed text into sound effects | Text to Audio | 1/6 seconds |
ElevenLabsVoice dubbing | Translate recorded speech into a different language | Audio to Audio | 1/2 seconds |
ElevenLabsVoice isolation | Isolate and remove noice from recorded speech | Audio to Audio | 1/6 seconds |
ElevenLabsSpeech to Speech | Transform recorded speech into a new voice | Audio to Audio | 1/3 seconds |
ElevenLabsEleven 3v | Expressive text to speech model with inline audio tags | Text to Audio | 1/characters |
ElevenLabsEleven v4 | Expressive text-to-speech for narration, dialogue, and voiceover, with audio tags and multi-voice scripts | Text to Audio | 1/50 characters |
ElevenLabsEleven Music v2.5 | Full songs or instrumentals from a prompt, with vocals steered by the prompt | Text to Music | 20/min |
| Ideogram — Image Generation | |||
IdeogramIdeogram 4 | high-fidelity text-to-image generation with precise graphic design layouts | Image to ImageText to Image | Turbo4/imgDefault7/imgQuality11/img |
IdeogramIdeogram P-Image | Generating images with accurate, legible text and typography | Text to Image | Very Low — 1K1/imgVery Low — 2K1/imgLow — 1K1/imgLow — 2K2/imgMedium — 1K2/imgMedium — 2K3/imgHigh — 1K2/imgHigh — 2K4/img |
IdeogramIdeogram 4.5 | Image generation and precise masked editing, from quick drafts to high fidelity | Text to ImageImage to Image | Low4/imgMedium8/imgHigh25/img |
IdeogramIdeogram Vector | Editable, scalable SVG graphics such as logos and icons, including converting an existing image to vector | Text to VectorImage to Vector | 17/img |
| MiniMax — Video Generation | |||
MiniMaxH3 | Multimodal video generation and editing | Text to VideoImage to VideoVideo to Video | 768p10/sec2K15/sec |
| Lightricks — Video Generation | |||
LightricksLTX 2.5 Fast | Fast, budget-friendly video generation with synced audio | Text to VideoAudio to VideoVideo to Video | 720p9/sec1080p13/sec1440p19/sec4K30/sec |
LightricksLTX 2.5 Pro | Quality-first video with native audio | Text to VideoAudio to VideoVideo to Video | 720p12/sec1080p17/sec |
| Fish — Audio Generation | |||
FishFish Audio | Budget-friendly & fast text-to-speech | Text to Speech | 1/250 characters |
FishFish Audio Drama 3 | Directable text-to-speech with plain-language cues for whispers, laughs, and emotion | Text to Speech | 1/250 characters |
| Recraft — Image Generation | |||
RecraftRecraft V4.1 Vector | Generating vector graphics as SVG files | Text to Image | 8/img |
RecraftRecraft V4.1 Flash | Fast, budget-friendly image generation | Text to Image | 1/img |
| Bria — Image Generation | |||
BriaFIBO 1.5 | Image generation from text or reference images | Text to ImageImage to Image | 1MP5/img4MP10/img |
BriaFIBO Edit 1.5 | Editing existing images | Image to Image | 5/img |
| Open Source — Image Generation | |||
Open SourceBiRefNet 2.0 | Remove an image’s background automatically for cutouts, masks, and composites | Remove background | 1/img |
| Mirelo — Audio Generation | |||
MireloMirelo SFX 2.0 | Generate synchronized sound effects and ambience for a video, or from a text prompt | Text to AudioVideo to Audio | 15/min |
| Krea — Image Generation | |||
KreaKrea Image 3 | Fast, realistic images with a natural style | Text to ImageImage to Image | 6/img |
| Tripo — 3D Generation | |||
TripoTripo H3.1 | Generating a 3D model from text or images | Text to 3DImage to 3D | Standard10/genStandard + texture (standard)20/genStandard + texture (detailed)30/genDetailed30/genDetailed + texture (standard)40/genDetailed + texture (detailed)50/gen |
Most advanced video generation with high realism and cinematography
Video editing and stylization
General-purpose video generation
Budget-friendly video generation
Character animation with a performance video (3 sec min)
Video editing and stylization
Convert any SDR video into professional-grade HDR
converts any video to the frame rate your delivery pipeline requires
Most advanced image generation and editing
Budget-friendly image generation
Combine multiple videos into a single clip
Add generated or uploaded audio to a video in Workflows
Extract audio from an uploaded or generated video
Real-time conversational AI avatars
Video generation with or without audio
Video generation with or without audio
General-purpose video generation
Budget-friendly video with audio
Budget-friendly image generation
Precision image generation and editing
Split any image into layers for editing
Fast, budget-friendly image generation with up to 10 reference images
Budget-friendly way to split any image into layers for editing
Multi-modal video generation with audio
Multi-modal video generation with audio, built for speed and exploration
Budget friendly video generation, built for speed and exploration
Continuous, high-fidelity audio-video clips with up to 50 multimodal reference
Generate multi-character dialogue, music, and ambient sound simultaneously
Most advanced video generation with audio and speech
Video editing and multi-modal generation
Most advanced and budget-friendly image generation
Most advanced image generation and editing
Budget-friendly image generation and editing
Fast and budget-friendly image generation
Advanced image generation and editing
Well-rounded and budget-friendly LLM for text processing, image analysis, and more in Workflows.
Generating music in Workflows
Generating music in Workflows
Expressive text-to-speech for voiceovers and narration
Budget-friendly, faster text-to-speech for narration and multilingual content
Most advanced video generation with audio and speech
Budget-friendly video generation
Previous-gen video generation with audio
Previous-gen budget-friendly video generation
Previous-gen budget-friendly video generation
Character animation with a performance video
Multi-modal video generation with audio
Budget friendly video generation built for speed and exploration
Long, continuous shots up to 30 seconds with keyframe control and multi-reference consistency
Advanced image generation
Budget-friendly image generation
Image generation with flexible balance of budget and quality
Fast image generation built for high volume and rapid iteration
High-fidelity precision-focused image generation
Advanced reasoning
Advanced image generation
Budget-friendly image generation
Advanced image generation and editing
use for creating long, continuous single-take shots
Upscaling video to 4K
Well-rounded and budget-friendly LLM for text processing, image analysis, and more in Workflows.
Flexible, customizable image upscaling
Transform an image by applying various artistic styles
Fast, budget-friendly image generation
Realism and precision for text-heavy, detailed images
Generating and editing images, with region edits and multi-image compositing
Fast, budget-friendly video generation with audio
fast, budget-friendly video editing and extending
Fast, budget-friendly video generation with audio
Faster, lower-cost Grok video generation with native audio
Turn typed text into speech
Turn typed text into sound effects
Translate recorded speech into a different language
Isolate and remove noice from recorded speech
Transform recorded speech into a new voice
Expressive text to speech model with inline audio tags
Expressive text-to-speech for narration, dialogue, and voiceover, with audio tags and multi-voice scripts
Full songs or instrumentals from a prompt, with vocals steered by the prompt
high-fidelity text-to-image generation with precise graphic design layouts
Generating images with accurate, legible text and typography
Image generation and precise masked editing, from quick drafts to high fidelity
Editable, scalable SVG graphics such as logos and icons, including converting an existing image to vector
Multimodal video generation and editing
Fast, budget-friendly video generation with synced audio
Quality-first video with native audio
Budget-friendly & fast text-to-speech
Directable text-to-speech with plain-language cues for whispers, laughs, and emotion
Generating vector graphics as SVG files
Fast, budget-friendly image generation
Image generation from text or reference images
Editing existing images
Remove an image’s background automatically for cutouts, masks, and composites
Generate synchronized sound effects and ambience for a video, or from a text prompt
Fast, realistic images with a natural style
Generating a 3D model from text or images