Plan the work
/write @anthropic.claude-sonnet-4-20250514 Create a campaign brief, image directions, video beats, and export checklist.Use text models when the output needs structure, decisions, copy, or a production plan.
Choose models by the output you need.
Explore 114+ public models from 38 providers, then route them through AskGL, editors, templates, and project workflows.
110 active or beta models / 3 legacy or deprecated models
19
Text and chat
55
Image
26
Video
19
Code
38
Providers
Models sit inside the request path.
Promptha does not need to pretend every model does every job. Use the model route that matches the output.
Generate the visual
/image @promptha.imagen-4-ultra Create a text-safe campaign image for the product. $landscape $quality:highUse image models when the request needs a visual output that can continue into an editor.
Create motion
/video @promptha.sora-2 Create an 8 second product spot with slow camera motion. $duration:8 $landscapeUse video models when the next output is a motion preview or a short creative cut.
Start with the models people compare most.
These model pages are strong decision anchors across text, image, video, code, and document workflows.
Anthropic / Text / premium
Claude Sonnet 4
Latest flagship reasoning
Open model pageOpenAI / Text / premium
GPT-4o
Flagship multimodal AI
Open model pageGoogle / Text / premium
Gemini 2.5 Pro
Most capable stable Gemini model for complex tasks requiring deep reasoning and analysis.
Open model pageBlack Forest Labs / Image / premium
Flux Pro
Professional-grade image generation. Excellent prompt following.
Open model pageGoogle / Video / premium
Veo 3.1
Google's advanced video AI
Open model pageDeepSeek / Text / budget
DeepSeek Chat
Powerful and cost-effective chat model from DeepSeek. Strong reasoning capabilities.
Open model pageShowing 114 of 114 models
Easel AI / face swap / Standard / Active
Advanced Face Swap
advanced-face-swap
Natural face swapping
Promptha / Image / Standard / Active
Aura Flow
aura-flow
Fast and efficient image generation model.
cjwbw / colorization / Budget / Active
BigColor
bigcolor
Fast colorization model for quick B&W to color conversion.
Promptha / Segmentation / Standard / Active
BiRefNet
birefnet
High-resolution dichotomous image segmentation for precise object extraction.
Bria / Background removal / Budget / Active
Bria Background Remove
bria-background-remove
Automated background removal from images with high accuracy.
Anthropic / Text / Budget / Legacy
Claude 3 Haiku
claude-3-haiku-20240307
Previous generation fast model. Consider upgrading to Claude 3.5 Haiku.
Anthropic / Text / Premium / Active
Claude 3 Opus
claude-3-opus-20240229
Most capable Claude 3 model for highly complex tasks requiring deep analysis.
Anthropic / Text / Standard / Legacy
Claude 3 Sonnet
claude-3-sonnet-20240229
Previous generation balanced model. Consider upgrading to Claude 3.5 Sonnet.
Anthropic / Text / Budget / Active
Claude 3.5 Haiku
claude-3-5-haiku-20241022
Fastest Claude model. Optimized for speed and cost while maintaining good quality.
Anthropic / Text / Premium / Active
Claude 3.5 Sonnet
claude-3-5-sonnet-20241022
Balanced model offering strong performance at a reasonable cost. Excellent for most tasks.
Anthropic / Text / Premium / Active
Claude Sonnet 4
claude-sonnet-4-20250514
Latest flagship reasoning
Clarity AI / Upscaling / Standard / Active
Crystal Upscaler
crystal-upscaler
AI image upscaler that preserves fidelity, color, and detail.
DeepSeek / Text / Budget / Active
DeepSeek Chat
deepseek-chat
Powerful and cost-effective chat model from DeepSeek. Strong reasoning capabilities.
DeepSeek / Code / Budget / Active
DeepSeek Coder
deepseek-coder
Specialized coding model from DeepSeek. Excellent for code generation and analysis.
Promptha / Depth / Standard / Active
Depth Anything V2
depth-anything-v2
Accurate depth maps
fofr / Face / Budget / Active
Face to Many
face-to-many
Transform faces into emoji, claymation, pixel art, or video game-style avatars.
Black Forest Labs / Image / Premium / Active
Flux 1.1 Pro
flux-1.1-pro
State-of-the-art image gen
Black Forest Labs / Image / Premium / Active
Flux 2
flux-2
Next generation Flux model with improved quality and prompt adherence.
Black Forest Labs / Image / Standard / Active
Flux 2 Flex
flux-2-flex
Flexible Flux 2 variant optimized for versatile image generation and editing.
Black Forest Labs / Image / Premium / Active
Flux 2 Pro
flux-2-pro
Professional tier Flux 2 with maximum quality and capabilities.
Black Forest Labs / Image / Standard / Active
Flux Dev
flux-dev
Development version of Flux. Good balance of quality and cost.
Black Forest Labs / Image / Premium / Active
Flux Kontext
flux-kontext
Context-aware image generation that maintains consistency across generations.
Black Forest Labs / Image / Premium / Active
Flux Kontext Pro
flux-kontext-pro
Pro version of Flux Kontext with enhanced context-aware generation and text rendering.
Black Forest Labs / Image / Premium / Active
Flux Pro
flux-pro
Professional-grade image generation. Excellent prompt following.
Black Forest Labs / Image / Premium / Active
Flux Pro 1.1 Ultra
flux-pro-1.1-ultra
Highest quality Flux model. Maximum detail and resolution.
Black Forest Labs / Image / Standard / Active
Flux Realism
flux-realism
Flux model fine-tuned for photorealistic output.
Black Forest Labs / Image / Budget / Active
Flux Schnell
flux-schnell
Lightning fast images
Black Forest Labs / Control / Standard / Active
FLUX.1 Canny Dev
flux-canny-dev
Open-weight edge-guided FLUX model for development.
Black Forest Labs / Control / Premium / Active
FLUX.1 Canny Pro
flux-canny-pro
Edge-guided generation
Black Forest Labs / Control / Standard / Active
FLUX.1 Depth Dev
flux-depth-dev
Open-weight depth-guided FLUX model for development.
Black Forest Labs / Control / Premium / Active
FLUX.1 Depth Pro
flux-depth-pro
Depth-guided generation
Black Forest Labs / inpainting / Standard / Active
FLUX.1 Fill Dev
flux-fill-dev
Open-weight FLUX inpainting model for development and fine-tuning.
Black Forest Labs / inpainting / Premium / Active
FLUX.1 Fill Pro
flux-fill-pro
Pro-grade inpainting
Promptha / inpainting / Standard / Active
Fooocus Inpaint
fooocus-inpaint
Multi-mode inpainting: fill areas, improve details (face/hands), or modify content.
Google / Text / Budget / Active
Gemini 1.5 Flash
gemini-1.5-flash
Fast and efficient Gemini model. Good for high-volume tasks.
Google / Text / Premium / Active
Gemini 1.5 Pro
gemini-1.5-pro
Most capable Gemini model with 1M token context window. Excellent for long documents.
Google / Text / Standard / Active
Gemini 2.0 Flash
gemini-2.0-flash
Fast and efficient Gemini model. Multimodal with massive context window.
Google / Text / Standard / Active
Gemini 2.5 Flash
gemini-2.5-flash
Stable production-ready Gemini model with excellent speed and quality balance. Great for high-volume applications.
Google / Text / Premium / Active
Gemini 2.5 Pro
gemini-2.5-pro
Most capable stable Gemini model for complex tasks requiring deep reasoning and analysis.
Google / Text / Standard / Active
Gemini 3 Flash
gemini-3-flash-preview
Google's latest AI
Runway / Image / Premium / Active
Gen-4 Image
gen4-image
Runway's Gen-4 image generation with advanced editing capabilities.
TencentARC / image restoration / Budget / Active
GFPGAN
gfpgan
Face restoration specialist. Reconstruct facial features from blurry or degraded images.
Promptha / Image / Premium / Active
GPT Image 1.5
gpt-image-1.5
ChatGPT image generation on Promptha
Promptha / Image / Premium / Active
GPT Image 2
gpt-image-2
Latest GPT image generation on Promptha
OpenAI / Text / Budget / Active
GPT-3.5 Turbo
gpt-3.5-turbo
Fast and cost-effective model for simpler tasks. Good balance of quality and speed.
OpenAI / Text / Premium / Legacy
GPT-4
gpt-4
Original GPT-4 model with strong reasoning capabilities.
OpenAI / Text / Premium / Active
GPT-4 Turbo
gpt-4-turbo
GPT-4 with improved instruction following, JSON mode, and vision capabilities.
MiniMax / Video / Standard / Active
Hailuo 2.3
hailuo-2.3
Latest Hailuo video model with improved motion and quality.
Tencent / Video / Standard / Active
Hunyuan Video
hunyuan-video
Tencent's video generation model. Open-source foundation with commercial quality.
Ideogram / Image / Standard / Active
Ideogram V3
ideogram-v3
Latest Ideogram with even better text rendering and design capabilities.
Ideogram / Image / Budget / Active
Ideogram V3 Turbo
ideogram-v3-turbo
Fastest and most affordable Ideogram V3 with excellent text rendering.
Promptha / outpainting / Standard / Active
Image Outpaint
image-outpaint
Extend images seamlessly
Google / Image / Standard / Active
Imagen 4 Fast
imagen-4-fast
Fast version of Imagen 4 optimized for speed while maintaining good quality.
Google / Image / Premium / Preview
Imagen 4 Preview
imagen4-preview
Google's latest image generation model with excellent prompt understanding.
Google / Image / Premium / Active
Imagen 4 Ultra
imagen-4-ultra
Highest-fidelity Imagen 4 output
ImagineArt / Image / Standard / Active
ImagineArt 1.5
imagineart-1.5
Professional-grade visuals with lifelike realism, strong aesthetics, and accurate text rendering.
Kuaishou / Video / Premium / Active
Kling O3 I2V Pro
kling-video-o3-i2v
Kling O3 pro image-to-video optimized for first/last frame transitions and style guidance.
Kwai / Video / Standard / Active
Kling V2.1
kling-v2.1
Official Kling V2.1 model optimized for stable motion and cinematic composition.
Kuaishou / Video / Standard / Active
Kling Video 2.6
kling-video-v2.6
Consistent character video
Kuaishou / Video / Standard / Active
Kling Video Image-to-Video
kling-video-i2v
Transform images into videos with Kling. Excellent at maintaining character and scene consistency.
Kuaishou / Video / Premium / Active
Kling Video V3 Pro I2V
kling-video-v3-pro-i2v
Kling 3.0 Pro image-to-video endpoint with cinematic motion and native media output.
mickeybeurskens / ocr / Budget / Active
LaTeX OCR
latex-ocr
Convert math equation images directly to LaTeX code.
Promptha / Image / Standard / Active
LongCat Image
longcat-image
6B parameter model excelling at multilingual text rendering, photorealism, and deployment efficiency.
Lightricks / Video / Standard / Active
LTX-2 19B I2V
ltx-2-19b-i2v
LTX-2 19B image-to-video model with native media-aware generation for richer outputs.
Lightricks / Video / Budget / Active
LTX-2 Image-to-Video
ltx-2-i2v
Animate images with LTX-2. Quick and cost-effective image-to-video generation.
Promptha / Depth / Standard / Active
Marigold Depth
marigold-depth
Diffusion-based depth estimation with fine details and sharp edges.
Google / Image / Premium / Active
Nano Banana 2
nano-banana-2
Google fast flagship image model
Promptha / Image / Standard / Active
Nano Banana Pro
nano-banana-pro
Google pro image generation
ByteDance / Video / Premium / Active
OmniHuman 1.5
omnihuman-v1.5
Advanced human generation and animation model.
Promptha / image restoration / Standard / Active
Photo Restoration
photo-restoration
Restore old photos
TencentARC / Face / Standard / Active
PhotoMaker
photomaker
Create photos of a person in various styles while preserving their identity.
PixVerse / Video / Standard / Active
PixVerse 5.5
pixverse-v5.5
Creative video generation model. Great for artistic and stylized video content.
flux-kontext-apps / Face / Standard / Active
Professional Headshot
professional-headshot
Instant pro headshots
Recraft / Image / Standard / Active
Recraft V3 SVG
recraft-v3-svg
Generate scalable vector graphics (SVG) from text prompts.
Recraft / Image / Standard / Active
Recraft V4 SVG
recraft-v4-svg
Generate current Recraft scalable vector graphics (SVG) from text prompts for editable design foundations.
Sourceful / Image / Standard / Active
Riverflow 2.0 Fast
riverflow-2.0-fast
Agentic image gen with typography
Promptha / Image / Budget / Active
Sana
sana
Fast and lightweight image generation model optimized for speed.
Stability AI / Image / Budget / Active
SDXL
sdxl
Stable Diffusion XL. Reliable baseline for image generation.
Promptha / Control / Standard / Active
SDXL ControlNet Union
sdxl-controlnet-union
All-in-one ControlNet
ByteDance / Video / Premium / Active
Seedance 2.0
seedance-2.0
ByteDance multimodal video model for text, image, video, and media-guided generation with multi-shot scene control.
ByteDance / Image / Standard / Active
Seedream 4
seedream-4
Text-to-image and single-sentence editing at up to 4K resolution.
ByteDance / Image / Premium / Active
Seedream 4.5
seedream-4.5
ByteDance's unified image generation and editing model. Supports up to 4K resolution.
OpenAI / Video / Premium / Active
Sora 2 Image-to-Video
sora-2-i2v
Animate images into videos using Sora 2. Transform still images into dynamic video content.
Stability AI / Image / Standard / Active
Stable Diffusion 3
sd3
Latest Stable Diffusion with improved text rendering and composition.
Stability AI / Image / Premium / Active
Stable Diffusion 3.5 Large
sd3.5-large
Latest Stable Diffusion with 8B parameters. Superior quality and prompt understanding.
jingyunliang / image restoration / Standard / Active
SwinIR
swinir
General image restoration: denoising, deblurring, and super-resolution.
Promptha / Video / Standard / Active
Sync Lipsync V2
sync-lipsync-v2
Advanced lipsync technology for realistic talking videos.
abiruyt / ocr / Budget / Active
Text Extract OCR
text-extract-ocr
Simple, versatile text extraction from any image.
Google / Video / Premium / Active
Veo 3
veo-3
Google official Veo 3 model for high-fidelity video generation with strong motion realism.
Google / Video / Standard / Active
Veo 3.1 Fast
veo-3.1-fast
Faster version of Veo 3.1 optimized for quick video generation with good quality.
Google / Video / Premium / Active
Veo 3.1 Image-to-Video
veo-3.1-i2v
Convert images to video using Google's Veo 3.1. Animate still images with natural motion.
Alibaba / Video / Standard / Active
Wan 2.2 Image-to-Video
wan-2.2-i2v
Alibaba's image-to-video model. Efficient and reliable video generation from images.
Wan Video / Video / Standard / Active
Wan 2.5 Image-to-Video
wan-2.5-i2v
Animate images into videos with natural motion and high fidelity.
Wan Video / Video / Standard / Active
Wan 2.5 Text-to-Video
wan-2.5-t2v
High-quality text-to-video generation with smooth motion.
Tongyi / Image / Budget / Active
Z-Image Turbo
z-image-turbo
Super-fast 6B parameter text-to-image model with LoRA support.
Turn model research into product choices
Move from the model directory into comparisons, roundups, workflow guides, and pricing.
Compare Models
See side-by-side model and platform comparisons.
ExploreBest-of Roundups
Use curated roundups for image, video, and writing tool decisions.
ExploreSee Real Use Cases
Find production workflows where these models fit naturally.
ExploreView Pricing
Connect model usage patterns to plans, credits, and budget expectations.
ExploreReady to start creating?
Use these models through Promptha without managing separate creative workflows across every provider.