32 use cases · 1,219 AI models · one interface Intelligence Index Claude Opus 5.5 leads with 58 points

What OMVIN Does for You with Over 1,000 AI Models

One sentence is enough: tell OMVIN what to do – and which model to use, if you have one in mind. If not, OMVIN picks the right one itself. This page shows everything that’s connected: 1,219 models at a glance.

Get started Intelligence Index
  • Claude Fable 5.1
  • Claude Haiku 5.5 New
  • GPT-6 Astra
  • MiMo 2.6
  • Gemini
  • Grok
  • GPT Image
  • Flux
  • Wan
  • Veo
  • Seedance
  • Kling
  • ElevenLabs
  • MiniMax Music
Intelligence Index

How smart is your agent?

In OMVIN, an agent carries out every task: a language model that plans, writes, codes and, when needed, calls the specialist models for image, video and voice. How well it thinks is measured by the Intelligence Index — determined independently. You name the model for your task or ask OMVIN which one it recommends.

How the index works 10 demanding tests, weighted across four categories
  • Agentic tasks30%
  • Coding20%
  • Scientific reasoning20%
  • General tasks30%
New in OMVIN

Claude Haiku 5.5 by Anthropic · since 8 October 2026

  • 43 index points
  • $0.21 per task
  • 243 tokens/s
Intelligence relative to

Efficiency line: connects the models for which no other model is both smarter and cheaper.Efficiency line: connects the models for which no other model is both smarter and faster.

In short

On the efficiency line: MiMo 2.6 Flash, GPT-6 Luna, MiMo 2.6 Pro, GPT-6.1 Sol, GPT-6 Astra and Claude Opus 5.5. Cost per task ranges from $0.06 to $7.63 — more than a hundredfold.On the efficiency line: Claude Opus 5.5 and Claude Haiku 5.5. Claude Haiku 5.5 writes 243 tokens per second, more than six times as fast as MiMo 2.6 Pro.

Agent models in OMVIN compared, source Artificial Analysis, as of 8 October 2026
ModelProviderIntelligence Index (points)Cost per task (US dollars)Speed (tokens per second)On the efficiency line
Claude Opus 5.5Anthropic58$5.9896Cost, Speed
Claude Fable 5.1Anthropic53$7.6368no
GPT-6 AstraOpenAI53$3.2646Cost
GPT-6.1 SolOpenAI52$0.7255Cost
GPT-6 SolOpenAI48$1.0485no
MiMo 2.6 ProXiaomi46$0.1340Cost
Claude Haiku 5.5 (new in OMVIN since 8 October 2026)Anthropic43$0.21243Speed
GPT-5.6 TerraOpenAI42$1.40108no
GLM 5.3 FlashZhipu AI42$0.2551no
DeepSeek V4.1 FlashDeepSeek39$0.27223no
Claude Sonnet 5Anthropic38$5.0979no
GPT-6 LunaOpenAI38$0.07127Cost
MiMo 2.6 FlashXiaomi38$0.0657Cost

Source: Artificial Analysis (Intelligence Index v4.3.2), as of 8 October 2026. Measured at each model’s highest reasoning level. Cost: what the provider charges on average for one index task — a measure of cost-efficiency, not your price in OMVIN. Speed: tokens (word fragments) generated per second, measured continuously. For your own tasks, the ranking may differ.

What’s possible

What OMVIN does for you.

32 concrete use cases in five areas, from image to text. For each, we name the three best models — the first is our recommendation.

  1. Browse Scroll through the overview and see what’s possible in each area and which AI models are suitable — nothing is triggered yet.
  2. Give the task Tell OMVIN in one sentence what you need and which model to use — say, Seedance for videos or GPT Image for images. Not sure? Ask OMVIN which model it recommends for your task.
  3. Get the result OMVIN calls the model you chose via the API and delivers the finished result to you.
01 · 10 use cases

Image

Create new visuals, edit photos, cut them out and sharpen them — from ad images to team photos.

AI-generated ad photo: a floating chocolate bar circled by liquid chocolate, cocoa powder and hazelnuts
Food ad from one sentence

Turn text into images

Product shots, social posts, invitations or posters from a description — photorealistic or illustrated

OMVIN uses
  1. GPT Image 2
  2. Nano Banana Pro
  3. Seedream 5.0 Pro
All 168 models for this
AI-generated OMVIN ad post: on the left a photo of a tradesman in his workshop, on the right on a dark panel the headline ‘Type the ad. Get the image.’ in a lime-cyan gradient and three benefits with lime ticks — ‘Text sits cleanly in the image’, ‘Done in minutes’, ‘For social and print’
Job ad with benefits

Image with text & layout

Job ads, menu boards, explainer graphics and posters with legible lettering right in the image

OMVIN uses
  1. GPT Image 2
  2. Ideogram V4.0
  3. Nano Banana Pro
All 72 models for this

Logos, icons and vector art

Logos, pictograms and print-ready graphics as a scalable vector file

OMVIN uses
  1. Recraft V4.1 Vector
  2. Recraft V4 Vector Pro
  3. Vecglypher
All 13 models for this

Edit images by instruction

Swap objects, change the time of day, rotate the view or restyle — with one sentence instead of Photoshop

OMVIN uses
  1. Nano Banana 2
  2. GPT Image 2
  3. FLUX.1 Kontext
All 159 models for this

Cut out and swap backgrounds

Cleanly cut out products, people or objects and place them on a new background

OMVIN uses
  1. Birefnet V2
  2. Bria RMBG 2.0
  3. Bria Background Replace
All 22 models for this

Remove clutter, extend images

Retouch away cables, passers-by or lettering and extend the image for any format

OMVIN uses
  1. Bria Eraser
  2. FLUX.1 pro Fill
  3. Finegrain Eraser
All 42 models for this

Upscale and restore

Make old family photos, phone pictures or small logos sharp and print-ready

OMVIN uses
  1. Topaz Upscale Precision
  2. SeedVR2
  3. Clarity Upscaler
All 47 models for this

Product photos and virtual try-on

Try clothes on a model, stage products — no photo studio needed

OMVIN uses
  1. FASHN Try-On 1.6
  2. FLUX Pro Try-On
  3. Bria Product Shot
All 22 models for this

Portraits & team shots

CV photos, consistent staff portraits or your own face in new scenes

OMVIN uses
  1. PuLID Flux
  2. Ideogram V3 Character
  3. Headshot Generator
All 24 models for this

Read and analyse images

Recognise text on receipts and delivery notes, count objects, describe photos automatically

OMVIN uses
  1. Florence-2 Large
  2. Moondream 3
  3. GOT OCR 2.0
All 53 models for this
02 · 10 use cases

Video

Videos from a sentence or a photo, with sound, subtitles and a talking avatar — no camera, no editing.

Jungle flight with OMVIN lettering, 36 s

Text to video

Commercials, reels and brand films from a description — no shoot, no editing

OMVIN uses
  1. Veo 3.1
  2. Kling Video v3 Pro
  3. Seedance 2.5
All 113 models for this

Bring photos to life

Listing photos become a tour, dishes steam, products spin — from a single image

OMVIN uses
  1. Kling Video v3 Pro
  2. Seedance 2.5
  3. MiniMax H3 Max
All 151 models for this

Video with audio

Clips that come with sounds, voice and music built in — no audio post-production

OMVIN uses
  1. Veo 3.1
  2. Ovi
  3. LTX 2.5
All 55 models for this

Talking avatar

A photo plus text becomes a website greeting or an announcement with a face

OMVIN uses
  1. Kling AI Avatar v2 Pro
  2. Omnihuman 1.5
  3. Heygen Digital Twin
All 38 models for this

Lip-synced translation

Existing videos in other languages — lip movement fits the new audio track

OMVIN uses
  1. sync-3 Lipsync
  2. Sync Lipsync 2.0
  3. ElevenLabs Dubbing
All 22 models for this

Edit videos by instruction

Change the style, swap objects, extend or reframe a clip — with a sentence

OMVIN uses
  1. Kling O3 Edit Pro
  2. Wan 3.0 Prime
  3. Gemini Omni Flash 1.1
All 79 models for this

Improve video quality

Denoise and sharpen phone footage and old films and bring them up to 4K

OMVIN uses
  1. Topaz Video Precision
  2. SeedVR2
  3. Bytedance Upscaler
All 26 models for this

Remove video backgrounds

Cut out people and products in video — green screen with no green screen

OMVIN uses
  1. Bria VRMBG 3.0
  2. Pixelcut Video
  3. Segment Anything 3
All 14 models for this

Subtitles and tagging

Generate subtitles automatically, summarise videos and make them searchable

OMVIN uses
  1. Wizper
  2. Subtitles
  3. Auto Subtitle
All 11 models for this

Add sound to silent videos

Generate fitting sounds and music for AI videos or edited footage

OMVIN uses
  1. MMAudio V2
  2. Mirelo SFX 1.6
  3. Hunyuan Video Foley
All 18 models for this
03 · 6 use cases

Voice & audio

Have texts read aloud naturally, transcribe conversations, create music and sounds — in any language.

Text to speech

Phone greetings, voice-overs for videos or your own audiobook — natural and multilingual

OMVIN uses
  1. ElevenLabs Eleven v3
  2. MiniMax Speech 2.8 HD
  3. Gemini 3.1 Flash TTS
All 50 models for this

Your voice as a greeting

The owner’s voice speaks the hold message and explainer video — only with her consent

OMVIN uses
  1. MiniMax Voice Cloning
  2. Qwen 3 TTS Clone
  3. Zonos Audio Clone
All 20 models for this

Speech to text

Site measurements by voice memo, dictation, meetings and voice messages as clean text

OMVIN uses
  1. ElevenLabs Scribe V2
  2. Wizper
  3. Cohere Transcribe
All 11 models for this

Royalty-free music

Background music for videos and in-store sound, jingles or a song for an anniversary

OMVIN uses
  1. ElevenLabs Music
  2. MiniMax Music 3
  3. Lyria 3 Pro
All 39 models for this

Sound effects

Sounds for explainer videos, apps and presentations from a description

OMVIN uses
  1. ElevenLabs Sound Effects V2
  2. Mirelo SFX 1.6
  3. Stable Audio 3 SFX
All 30 models for this

Clean recordings

Remove noise and reverb, isolate voices, split music into stems

OMVIN uses
  1. ElevenLabs Audio Isolation
  2. DeepFilterNet 3
  3. Demucs
All 7 models for this
04 · 2 use cases

3D

Finished 3D models from a photo or a description — for your shop, planning and 3D printing.

3D model from photo or text

Products for your shop, components for planning or figures for 3D printing

OMVIN uses
  1. Hunyuan 3D Pro
  2. Trellis 2
  3. Tripo H3.1
All 44 models for this

Refine 3D models

Clean geometry, new textures and a skeleton for animation

OMVIN uses
  1. Meshy Rigging
  2. Hunyuan 3D Smart Topology
  3. Tripo3D Remesh
All 11 models for this
05 · 4 use cases

Text & code

Write texts, analyse documents, research — and build finished tools and websites from one sentence.

Write and revise texts

Quotes, emails, applications and website copy — in the right tone, without typos

OMVIN uses
  1. Claude Fable 5.1
  2. GPT-6 Astra
  3. Gemini 3.7

Analyse documents and data

Summarise contracts, analyse spreadsheets, condense market data into a recommendation

OMVIN uses
  1. Claude Fable 5.1
  2. Gemini 3.7
  3. GPT-6 Astra

Build apps & calculators

Landing page, mortgage calculator or booking tool from one sentence — ready to embed

OMVIN uses
  1. Claude Fable 5.1
  2. GPT-6 Astra
  3. Grok 4.6

Research and translation

Find current information, check sources, translate texts into any language

OMVIN uses
  1. Grok 4.6
  2. Gemini 3.7
  3. Claude Fable 5.1
Text & code

One sentence. Fully built.

OMVIN does more than write text: it builds you finished tools. Four examples from a property project, each created from a single sentence — landing page, calculator, market analysis, brochure.

Build a landing page for this flat — commission⁠-⁠free, with a viewing button.

Landing page, fully built

Build a cost calculator for our clients.

Calculator tool to embed

Analyse the local market and show me prices and demand.

Market dashboard

Turn this into a finished brochure ready to send.

Brochure layout
Model directory

All models. Complete.

1,219 models in 27 categories, as of 7 October 2026. Above, each use case shows the top three — here is the rest. Pick a use case and only the models that serve it remain; the recommendations from above are marked.

Image546 models

Edit image402 endpoints

  • Nano Banana Pro
  • Nano Banana 2
  • GPT Image 2.5 Sunburst Edit
  • GPT Image 2 API
  • GPT Image 2.5 Flare Edit
  • Nano Banana
  • Birefnet Background Removal V2
  • Seedream 5.0 Pro Image Editing
  • FLUX.1 Kontext [pro]×2
  • Bytedance Seedream V4.5 Edit
  • SeedVR2×2
  • FLUX 2 Pro Edit
  • Bria RMBG 2.0
  • Flux 3 Image
  • Upscale Images
  • Segment Anything Model 3
  • Bytedance Seedream V4 Edit
  • Ideogram V4.5 Edit
  • Grok Imagine Image
  • Birefnet Background Removal
  • Meta Muse Image Edit
  • Nano Banana Lite Edit
  • Clarity Upscaler
  • FLUX.1 [pro] Fill
  • Grok Imagine Image 2.0
  • FLUX.2 [klein] 9B
  • Topaz Upscale Image Precision
  • Gemini 3 Pro Image Preview
  • GPT-Image 1.5
  • Gemini 2.5 Flash Image
  • FLUX 2 Edit
  • Bria Expand Image
  • Recraft Crisp Upscale
  • Pixelcut Background Remover
  • FLUX.1 Kontext [max]×2
  • Ffmpeg Api
  • Seedream×3
  • AuraSR
  • Qwen Image Edit 2511×2
  • Ideogram Remove Background
  • Remove Background
  • Qwen Image Edit 2511 Multiple Angles
  • Qwen Image 3 Image Editing
  • Topaz Upscale Image Generative
  • Flux 2 Max
  • Recraft
  • FLUX 2 Flash Edit
  • Bria Eraser
  • FLUX.1 [dev]×2
  • Image Preprocessors×10
  • FLUX.2 [klein] 4B
  • Gemini 3.1 Flash Image Preview
  • FLUX.1 Kontext [dev]
  • Segment Anything Model 2×2
  • Crystal Upscaler
  • Grok Imagine Image Editing Quality
  • Sam 3 1×2
  • Seedream 5.0 Pro Layerize
  • FLUX 2 Pro Outpaint
  • FASHN Virtual Try-On V1.6
  • FLUX 2 Turbo Edit
  • PuLID Flux
  • EVF-SAM2 Segmentation
  • Qwen Image Edit×3
  • Z Image Turbo Image To Image
  • Qwen Image Edit Plus
  • Kling Image×2
  • Flux 2 Flex
  • Flux Kontext Lora×2
  • Qwen Image Layered×2
  • Flux Pro Erase
  • CodeFormer
  • Wan×3
  • FLUX.1 [dev] with LoRAs
  • Topaz Upscale Image Creative
  • FLUX 2 Lora Edit
  • Image Outpaint
  • gpt-image-1
  • Sam 3
  • Hunyuan Image
  • PATINA×2
  • Midas Depth Estimation
  • Wan v2.6 Image to Image
  • Ideogram V3 Character
  • Topaz Upscale Image Transparent
  • FLUX.2 [klein] 9B Base LoRA
  • Mai Image 2.5
  • Bria Increase Resolution: Upscale Images up to 4x Without Losing Detail | fal
  • Florence-2 Large×8
  • FLUX.1 [dev] with Controlnets and Loras×4
  • FLUX.2 [klein] 9B LoRA
  • Finegrain Eraser Mask
  • FLUX.2 [klein] 9B Base
  • Feynobg Background Remover
  • Image Editing Photo Restoration
  • Bria Product Shot
  • Ideogram V3 Edit
  • Bria Background Replace
  • Kling O1 Image
  • Object Removal×4
  • IC-Light-v2 for Image Relighting
  • Virtual Try-on
  • Ideogram×3
  • Bria Virtual Try-On (FIBO-Edit-1.5)
  • FLUX.1 [dev] Fill with LoRAs
  • Marigold V2 Depth
  • Smart Resize
  • Workflow Utilities Extract Nth Frame
  • GPT Image 1 Mini
  • DDColor
  • Fibo Edit 1.5 Image Editing
  • Ideogram Object Removal
  • FLUX.2 [klein] 4B Base
  • Phota
  • Luma Uni-1 Edit
  • Marigold Depth Estimation
  • MAI Image 2.5 Pro (Edit)
  • Google Virtual Try On
  • Ideogram V4.0q Image to Image
  • Topaz Restore Image
  • Recraft V3
  • Luma Uni-1 Edit Max
  • Recraft Creative Upscale
  • FLUX Virtual Try-On
  • Hy Wu Edit
  • Image Editing Reframe
  • Fibo Edit
  • Image2svg
  • Flux 2 [klein] Realtime
  • Stable Diffusion XL×2
  • Photo Restoration
  • Qwen Image Edit Plus Lora Gallery×10
  • Image Editing Text Removal
  • Z Image Turbo Image To Image Lora
  • Ideogram V3 Character Edit
  • Hidream O1 Image×2
  • FASHN Virtual Try-On V1.5
  • Topaz Adjust Image
  • Instant Character
  • ben-v2-image
  • Luma Photon Flash Reframe
  • Rembg Enhance (Remove Background Enhance)
  • Creative Upscaler
  • Z Image Turbo Inpaint
  • DWPose Pose Prediction
  • Extract Object
  • Hunyuan World
  • Face Retoucher
  • Phota Enhance
  • FILM
  • Topaz Sharpen Image
  • Image Editing Object Removal
  • Qwen Image Max
  • Z Image Turbo Controlnet
  • Flux 2 Lora Gallery×5
  • Qwen Image
  • Wan 2.5 Image to Image
  • Upscale
  • Qwen Image Edit 2509
  • PuLID
  • DRCT-Super-Resolution
  • Image2Pixel
  • FLUX1.1 [pro] ultra Redux
  • Topaz Denoise Image
  • Firered Image Edit V1.1
  • Bria GenFill
  • Age Modify
  • Glm Image
  • Stable Diffusion with LoRAs×2
  • Hair Change
  • Minimax Image Subject Reference
  • FLUX.1 Krea [dev]×2
  • FLUX.2 [klein] 4B LoRA
  • Image Editing Realism
  • Live Portrait
  • Image Editing Hair Change
  • FLUX1.1 [pro] Redux
  • FLUX.1 [dev] Control LoRA Depth
  • Fibo Edit [Relight]
  • Ideogram Replace Background
  • Relighting
  • Fibo Edit [Restore]
  • Flux Vision Upscaler
  • Qwen Image Edit Plus Lora
  • try-on
  • FLUX.2 [klein] 4B Base LoRA
  • FLUX.1 [dev] Depth with LoRAs
  • Bria Product Holding (FIBO-Edit-1.5)
  • Boogu Image
  • Genfill
  • Moondream3 Preview [Segment]
  • Image Editing Background Change
  • Ideogram Upscale
  • Firered Image Edit
  • Stable Diffusion XL Lightning×2
  • Ideogram V4.0q Tiling
  • NAFNet-deblur
  • Post Processing
  • Longcat Image
  • FLUX.1 Krea [dev] with LoRAs
  • Image Editing Retouch
  • Pixelcut Product Photo
  • Chrono Edit
  • Leffa Virtual TryOn
  • Latent Consistency Models (v1.5/XL)×2
  • Post Processing Sharpen
  • Stable Diffusion V3
  • Vidu×2
  • MoonDreamNext Detection
  • Telestyle V2 Style Transfer
  • Fibo Edit [Erase by Text]
  • IP Adapter Face ID
  • Bagel
  • SDXL ControlNet Union×2
  • Replace Background
  • Fibo Edit [Colorize]
  • Makeup Changer
  • Luma Photon Reframe
  • Style Transfer
  • Juggernaut Flux Pro
  • FLUX.1 Krea [dev] Inpainting with LoRAs
  • FLUX.1 [dev] Control LoRA Canny
  • Expression Change
  • Product Holding
  • PhotoMaker
  • Joyai Image Edit
  • Headshot Generator
  • FLUX.1 SRPO [dev]×2
  • DreamOmni2
  • Portrait Enhance
  • FLUX.1 [dev] Canny with LoRAs
  • Hi3D Image to Relief
  • Z Image Turbo Inpaint Lora
  • Qwen Image Edit 2509 Lora Gallery×10
  • Image Editing Face Enhancement
  • Perspective Change
  • Z Image Turbo Controlnet Lora
  • Cartoonify
  • Image Editing Color Correction
  • Ideogram V2 Remix
  • NAFNet-denoise
  • Emu 3.5 Image
  • Ideogram V3 Character Remix
  • Image Editing Cartoonify
  • FLUX.1 [schnell] Redux×2
  • Image Editing Expression Change
  • Uso
  • Finegrain Eraser
  • Vecglypher
  • Optimized Latent Consistency (SDv1.5)
  • FLUX.1 [dev] Redux×2
  • Bernini-R Edit Image
  • Image Editing Plushie Style
  • Product Photography
  • Playground v2.5×2
  • Kolors Image to Image
  • ControlLight
  • Embed Product
  • Post Processing Blur
  • Image Editing Style Transfer
  • Omni Zero
  • Ghiblify Images
  • Inpainting sdxl and sd
  • RIFE
  • Post Processing Color Correction
  • Fibo Edit [Restyle]
  • Image Editing Professional Photo
  • Qwen Image Edit Lora
  • Image Editing
  • Bria
  • Qwen Image Edit 2509 Lora
  • Stepx Edit2
  • Fibo Edit [Rewrite Text]
  • Leffa Pose Transfer
  • Bria Product Dimensions
  • Hidream I1 Full
  • Ideogram V4.0q Image to Image LoRA
  • Image Editing Wojak Style
  • Luma Photon×2
  • Post Processing Grain
  • Chrono Edit Lora
  • Fibo Edit [Reseason]
  • Finegrain Eraser Bbox
  • Fibo Edit [Add Object by Text]
  • Image Editing Youtube Thumbnails
  • Fibo Edit [Sketch to Image]
  • Image Editing Age Progression
  • Juggernaut Flux Base
  • Texture Transform
  • City Teleport
  • Fibo Edit [Replace Object by Text]
  • Fibo Edit [Blend]
  • Ideogram V2 Turbo Remix
  • FLUX.1 Krea [dev] Redux×2
  • ControlNet SDXL×2
  • Uno
  • Juggernaut Flux Lora
  • PASD
  • Image Editing Time Of Day
  • Image Editing Broccoli Haircut
  • Image Editing Scene Composition
  • Chrono Edit Lora Gallery×2
  • Ideogram V2A Remix
  • FLUX.1 [pro] Fill Fine-tuned
  • Photography Effects
  • Image Editing Weather Effect
  • Ideogram V2A Turbo Remix
  • Invisible Watermark
  • Ideogram V4.0q Tiling LoRA
  • Ideogram V2 Edit
  • Flow-Edit
  • DocRes
  • DocRes-dewarp
  • Post Processing Dissolve
  • Ideogram V2 Turbo Edit
  • Post Processing Dodge Burn
  • Post Processing Desaturate
  • Post Processing Chromatic Aberration
  • Post Processing Color Tint
  • Post Processing Parabolize
  • Post Processing Solarize
  • Post Processing Vignette
  • Nano Banana 2.1 Edit

Text to image203 endpoints

  • FLUX.1 [schnell]×2
  • Nano Banana Pro
  • Nano Banana 2
  • GPT Image 2 API
  • GPT Image 2.5 Flare Text to Image
  • FLUX.1 [dev]×2
  • GPT Image 2.5 Sunburst Text to Image
  • Flux 2 Pro
  • Nano Banana
  • FLUX1.1 [pro]
  • Seedream 5.0 Pro Text to Image
  • FLUX1.1 [pro] ultra
  • Z Image Turbo
  • Bytedance Seedream V4.5 Text To Image
  • FLUX.2 [klein] 9B
  • FLUX.1 [dev] with LoRAs
  • Bytedance Seedream V4 Text To Image
  • FLUX 2
  • Flux 3 Image
  • Nano Banana 2 Lite
  • Grok Imagine Image×2
  • Ideogram Text to Image
  • Meta Muse Image Text to Image
  • Krea 2 Large
  • FLUX 2 Flash
  • Ideogram V4.5 Text to Image
  • Recraft V3
  • FLUX 2 Turbo
  • Grok Imagine Image 2.0
  • GPT-Image 1.5
  • Stable Diffusion XL
  • FLUX.2 [klein] 4B
  • Flux 2 Max
  • Krea 2 Turbo
  • Qwen Image 3 Text to Image
  • Ideogram V4.0 Text to Image
  • Qwen Image
  • Seedream×2
  • Gemini 3 Pro Image Preview
  • Recraft V4.1 Text to Image
  • Gemini 2.5 Flash Image
  • FLUX.1 Kontext [pro]
  • Recraft V4
  • Krea 2 Text to Image Turbo LoRA
  • Nano Banana Lite
  • Recraft V4.1 Text to Vector
  • Flux 2 Flex
  • Recraft V4.1 Flash Text to Image
  • FLUX 2 Lora
  • Gemini 3.1 Flash Image Preview
  • Z Image Turbo Lora
  • PATINA
  • Qwen Image 2512×2
  • gpt-image-1
  • Krea 2 Medium
  • FLUX.1 [dev] with Controlnets and Loras
  • Stable Diffusion XL Lightning
  • Recraft V4 Pro
  • Recraft V4.1 Text to Image Pro
  • Kling Image×2
  • Recraft V4 (Vector)
  • Mai Image 2.5 Text to Image
  • GPT Image 1 Mini
  • MiniMax (Hailuo AI) Text to Image
  • Wan×4
  • Sana
  • FLUX.1 [dev] Inpainting with LoRAs
  • FLUX.1 Krea [dev]×2
  • Hunyuan Image×2
  • FLUX.1 Kontext [max]
  • Ideogram V2
  • V4.0q [instant]
  • Z-Image Turbo Seamless Tiling
  • V4.0q [fast]
  • Luma Uni-1 Text to Image
  • Ideogram Transparent
  • Stable Diffusion 3.5 Large
  • Krea 2 Medium Text to Image Turbo
  • Stable Diffusion with LoRAs
  • Z Image Base
  • Luma Uni-1 Text to Image Max
  • Hidream I1 Fast
  • Recraft V4.1 Text to Vector Pro
  • MAI Image 2.5 Pro (Text to Image)
  • Recraft V4 Styles Text to Image
  • Hunyuan Image 3.0 Instruct
  • Ernie Image Turbo
  • FLUX 2 Lora Gallery Realism
  • Hidream O1 Image×2
  • FLUX.1 [dev] Control LoRA Depth
  • FLUX.2 [klein] 9B Base
  • FLUX.2 [klein] 9B LoRA
  • Recraft V4 Styles Text to Vector
  • Recraft V4 Styles Pro Text to Image
  • Hidream I1 Full
  • FLUX.2 [klein] 9B Base LoRA
  • FLUX.1 [dev] Control LoRA Canny
  • Stable Diffusion V3
  • Wan v2.6 Text to Image
  • Krea 2 Text to Image Turbo Style
  • Recraft V4 Pro (Vector)
  • Recraft 20b
  • Wan 2.5 Text to Image
  • Recraft V4.1 Text to Image Utility
  • Sana Sprint
  • Phota Text to Image
  • Cosmos 3 Super
  • Ernie Image
  • Juggernaut Flux Lightning
  • FLUX.1 Krea [dev] with LoRAs
  • Playground v2.5
  • Luma Photon
  • Stable Diffusion 3.5 Medium
  • FLUX.2 [klein] 4B Base
  • Recraft V4.1 Utility Text to Image
  • Nucleus Image
  • Fibo Gen 1.5 Text to Image
  • Fooocus Inpainting
  • Realistic Vision
  • Ideogram V2 Turbo
  • Kolors
  • Qwen Image Max
  • Illusion Diffusion
  • Boogu Image
  • Fibo
  • Recraft V4 Styles Pro Text to Vector
  • GLM Image
  • Longcat Image
  • Ideogram V2A Turbo
  • Stable Diffusion v1.5
  • Juggernaut Flux Base LoRA
  • FLUX.2 [klein] 4B LoRA
  • AuraFlow
  • Pony V7
  • FLUX.1 SRPO [dev]×2
  • Juggernaut Flux Pro
  • Luma Photon Flash
  • Sana v1.5 4.8B
  • Hidream I1 Dev
  • OmniGen v1
  • CogView
  • Flux Kontext Lora
  • Lumina Image 2
  • FLUX.1 Subject
  • Wan v2.2 A14B Text-to-Image A14B with LoRAs
  • Bria Text-to-Image Base
  • Fooocus×2
  • Sana v1.5 1.6B
  • Dreamshaper
  • ControlNet SDXL
  • SDXL ControlNet Union
  • Fibo Lite
  • DeepSeek Janus-Pro
  • Z Image Base Lora
  • Ovis Image
  • Omnigen V2
  • Ideogram V4.0q Text to Image (LoRA)
  • FLUX.2 [klein] 4B Base LoRA
  • Vidu
  • Bagel
  • Z-Image Turbo Seamless Tiling Lora
  • Sensenova U1 Infographic
  • Fibo Bbq Preview
  • Latent Consistency Models (v1.5/XL)
  • Bitdance
  • Ideogram V2A
  • Flux 2 Lora Gallery×4
  • Juggernaut Flux Base
  • Bria Text-to-Image Fast
  • Fooocus Image Prompt
  • Rundiffusion Photo Flux
  • Emu 3.5 Image
  • FLUX1.1 [pro] ultra Fine-tuned
  • Bria Text-to-Image HD
  • Ernie Image Lora Turbo
  • Ernie Image Lora
  • Vecglypher
  • FLUX 2 Lora Gallery Hdr Style
  • Flux Krea Lora
  • Fooocus Upscale or Vary
  • Flux Lora
  • Ideogram
  • PixArt-Σ
  • Stable Cascade
  • SoteDiffusion
  • Nano Banana 2.1

Vision34 endpoints

  • OpenRouter [Vision]
  • NSFW Filter
  • NSFW Checker
  • Video Understanding
  • Moondream3 Preview [Detect]
  • Moondream 3 Preview [Query]
  • Moondream2×4
  • Florence-2 Large×2
  • Florence 2 Large OCR
  • Moondream3 Preview [Point]
  • MoonDreamNext
  • Moondream3 Preview [Caption]
  • Florence 2 Large Detailed Caption
  • Isaac 0.1
  • Florence 2 Large Caption
  • LLaVA v1.6 34B
  • GOT OCR 2.0
  • Marlin
  • Sa2VA 8B Image
  • Moondream
  • Sa2VA 4B Image
  • Sam 3
  • Sa2VA 8B Video
  • Nemotron Diffusion Vlm
  • MoonDreamNext Batch
  • Scene Finder
  • Sa2VA 4B Video
  • Florence 2 Large Region To Category
  • Isaac 0.1 [OpenAI Compatible Endpoint]
  • Marlin Find

Analyse image3 endpoints

  • VGGT-1B
  • Bria Ad Delayer: Convert Flat Ads into Editable Layers | fal
  • Bagel

Structured image output3 endpoints

  • Fibo
  • Fibo Lite
  • Fibo Edit [Structured Instruction]

Describe image1 endpoint

  • Nemotron 3 Nano Omni
Video456 models

Image to video202 endpoints

  • Kling Video v3 Image to Video [Pro]
  • H3 Max Image to Video
  • H3 Max Turbo Image to Video
  • H3 Max Reference to Video
  • Seedance 2.5 Reference to Video
  • Kling Video×5
  • Seedance 2.5 Image to Video
  • Kling Video v3 Image to Video [Standard]
  • Kling Video v2.6 Image to Video
  • Seedance 2 Image to Video
  • Veo 3.1 Fast×3
  • MiniMax H3 Reference to Video
  • MiniMax H3 Image to Video
  • Seedance 2 Reference to Video
  • Veo 3.1×3
  • Veo3.1 Lite Image to Video
  • Wan 3.0×2
  • Bytedance Seedance V1.5 Pro Image To Video
  • Gemini Omni Flash 1.1 Image to Video
  • H3 Max Lip Sync Image to Video
  • Bytedance Omnihuman V1.5
  • Kling AI Avatar v2 Standard
  • Grok Imagine Video
  • Kling O3 Image to Video [Pro]×2
  • Kling AI Avatar v2 Pro
  • Grok Imagine Video 1.5
  • Kling O3 Reference to Video [Pro]
  • Seedance 2.5 US Reference to Video
  • Seedance 2.0 Fast Image to Video
  • Gemini Omni Flash 1.1 Reference to Video
  • Seedance 1.0 Pro
  • Bytedance Seedance V1 Pro Fast Image To Video
  • Kling Video V3 Turbo Pro Image to Video
  • Seedance 2.0 Fast Reference to Video
  • FLUX 3 Image to Video
  • Fabric 1.0
  • MiniMax Hailuo 02 [Standard] (Image to Video)
  • Kling Video V3 Standard Turbo Image to Video
  • Wan×2
  • Wan 3.0 Prime
  • Kling O3 Reference to Video [Standard]
  • PixVerse V6 Image To Video
  • Seedance 2.5 US Image to Video
  • Grok Imagine Video 1.5 Lite Image to Video
  • Gemini Omni Flash×2
  • Seedance 2.0 Mini Image to Video
  • Seedance 2.0 Mini
  • Heygen
  • Wan 2.5 Image to Video
  • Veo3.1 Lite FLF
  • Wan v2.2 A14B
  • H3 Max Camera Controls
  • LTX 2.3 Video Fast
  • Grok Imagine Video 1.5 Reference to Video
  • sync-3 Avatar Image to Video
  • Kling O1 First Frame Last Frame to Video [Pro]
  • MiniMax Hailuo 2.3 Fast [Standard] (Image to Video)
  • Grok Imagine Reference to Video
  • Flux 3 First Last Frame to Video
  • PixVerse Swap
  • Wan v2.6 Image to Video
  • LTX 2.5 Image to Video Fast
  • LTX 2.5 Image to Video Pro
  • MiniMax Hailuo 2.3 [Standard] (Image to Video)
  • Creatify Aurora
  • Luma Ray 3.2 Image to Video
  • MiniMax Hailuo 2.3 [Pro] (Image to Video)
  • Happy Horse×2
  • LTX 2.3 Video Pro
  • Seedance 2.0 US Reference to Video
  • MiniMax Hailuo 02 [Pro] (Image to Video)
  • Wan-2.1 Image-to-Video
  • PixVerse V6 Transition
  • Pixelcut Looping Video
  • Happy Horse 1.1 Image to Video
  • Ffmpeg Api Images to Video
  • Kling O1 Reference Image to Video [Pro]
  • Seedance 2.0 US Image to Video
  • Wan v2.2 5B
  • Vidu×7
  • OmniHuman
  • V2.6
  • Kling O1 First Frame Last Frame to Video [Standard]
  • Minimax
  • Flux 3 Image to Video
  • PixVerse C1 Image To Video
  • PixVerse V5.5 Image To Video
  • Happy Horse 1.1 Reference to Video
  • LTX Video (preview)
  • Wan 2.7 Reference to Video
  • Pika Image to Video (v2.2)
  • MiniMax Hailuo 2.3 Fast [Pro] (Image to Video)
  • PixVerse V5 Image To Video
  • Kling AI Avatar Pro
  • PixVerse V5.5 Effects
  • Flux 3 Image To Video Draft
  • MiniMax H3 Image to Video LoRA
  • Kling AI Avatar
  • PixVerse C1 Reference To Video
  • PixVerse V4.5 Image To Video
  • MuseTalk
  • Live Portrait
  • Fabric 1.0 Fast
  • Sad Talker×2
  • PixVerse V5 Transition
  • MiniMax (Hailuo AI) Video 01×2
  • LTX-Video 13B 0.9.8 Distilled
  • Wan-2.1 First-Last-Frame-to-Video
  • Wan v2.2 A14B Image-to-Video A14B with LoRAs
  • LTX-2.3 22B Distilled×2
  • LTX Video-0.9.7 13B Distilled
  • LTX-2.3 22B×2
  • Kling O1 Reference Image to Video [Standard]
  • Hunyuan Video Image-to-Video Inference
  • Ltx 2.3 Quality×3
  • Pika
  • LongCat Video Distilled×2
  • Wan Effects
  • Flux 3 Keyframes To Video Draft
  • Mirage Avatar X
  • Flux 3 First Last Frame to Video Draft
  • PixVerse C1 Transition
  • PixVerse V5.5 Transition
  • PixVerse V5 Effects
  • Ovi
  • PixVerse V4.5 Effects
  • Cosmos 3 Super Image to Video
  • PixVerse V4.5 Transition
  • Stable Video Diffusion Turbo
  • Hunyuan Video V1.5
  • Kandinsky5 Pro
  • Framepack×2
  • PixVerse V4 Image To Video
  • PixVerse V5.6 Image To Video
  • AI Avatar Multi
  • Vidu Start-End to Video
  • Wan-2.1 Pro Image-to-Video
  • High Quality Stable Video Diffusion
  • Vidu Image to Video×2
  • Pika Scenes (v2.2)
  • LongCat Video×2
  • Davinci Magihuman
  • Flashhead
  • Vidu Start End to Video
  • AI Avatar Single Text
  • CogVideoX-5B
  • Marey Realism V1.5
  • Framepack F1
  • Kandinsky 6.0 Lite
  • Wan-2.1 Image-to-Video with LoRAs
  • Cosmos Predict 2.5 2B
  • Vidu Template to Video
  • PixVerse V4 Effects
  • PixVerse V4.5 Image To Video Fast
  • Kandinsky 6.0 Pro
  • Vidu Reference to Video
  • PixVerse V5.6 Transition
  • MiniMax (Hailuo AI) Video 01 Director - Image to Video
  • PixVerse V4 Image To Video Fast
  • MiniMax (Hailuo AI) Video 01 Subject Reference
  • PixVerse V3.5 Image To Video
  • PixVerse V3.5 Transition
  • AMT Frame Interpolation
  • MAGI-1 (Distilled)
  • Bernini-R Reference to Video
  • PixVerse V3.5 Effects
  • PixVerse V3.5 Image To Video Fast
  • AI Avatar Multi Text
  • Pika Image to Video (v2.1)
  • Hunyuan Video Image-to-Video LoRA Inference
  • Pika Image to Video Turbo (v2)
  • Lynx
  • Decart

Edit video201 endpoints

  • sync-3 Lipsync
  • Kling O3 Edit Video [Pro]
  • Wan 3.0 Prime
  • Sync Lipsync 2.0
  • Kling Video×2
  • H3 Max Recast
  • Topaz Upscale Video Precision
  • Ffmpeg Api
  • Bytedance Upscaler Upscale Video
  • Sync Lipsync
  • LatentSync
  • Kling Video v2.6 Motion Control [Standard]
  • FFmpeg API Compose
  • SeedVR2
  • Wan-2.2 Animate Replace
  • Ffmpeg Api Merge Audio-Video
  • MMAudio V2
  • Kling O3 Edit Video [Standard]
  • Gemini Omni Flash 1.1 Edit
  • Kling O1 Edit Video [Pro]
  • Workflow Utilities Trim Video
  • Kling Video v2.6 Motion Control [Pro]
  • Topaz Upscale Video Generative
  • Lipsync
  • Lucy 2.5
  • Flux 3 FAST Edit Video
  • VEED Lipsync
  • Depth Anything Video
  • Kling O3 Reference Video to Video [Pro]
  • Subtitles
  • Bria's VRMBG 3.0
  • H3 Max Turbo Extend Video
  • Birefnet
  • Sam 3×2
  • sync.so -- lipsync 1.9.0-beta
  • H3 Max Extend Video
  • Bytedance Dreamactor V2
  • Video Background Removal×3
  • Workflow Utilities Scale Video
  • PixVerse Lipsync
  • Wan-2.2 Animate Move
  • Workflow Utilities Auto Subtitle
  • Kling O3 Reference Video to Video [Standard]
  • Gemini Omni Flash
  • Flux Video Upscale
  • Wan×2
  • Happy Horse Video Edit
  • H3 Max 3D to Video
  • Grok Imagine Video
  • Luma Ray 3.2 Reframe
  • Ltx 2.3
  • Heygen Lipsync - Precision
  • Luma Ray 3.2 Video to Video
  • RIFE
  • Infinitalk×2
  • H3 Max
  • Video×6
  • Sam 3 1×2
  • Kling Video 4K Video to Video
  • Flashvsr
  • Video Upscaler
  • Void Video Inpainting
  • Kling Video 4K Video to Video Edit
  • Flux 3 Extend Video
  • Kling O1 Edit Video [Standard]
  • Mirelo SFX1.6
  • Topaz Upscale Video Creative
  • Veo 3.1
  • Veo 3.1 Fast
  • Wan VACE 14B×6
  • Sync React-1
  • Pixelcut Video Background Removal
  • Mirelo SFX V1.5
  • Kling O1 Reference Video to Video [Pro]
  • Grok Imagine Extend Video
  • Lucy Restyle
  • Ben-Video-Bg-Rm
  • MiniMax H3 Reference to Video LoRA
  • Wan Motion
  • Ltx 2.3 Quality×19
  • FILM
  • Segment Anything Model 2
  • V1.1 Video to Video Music
  • Topaz Interpolate Video
  • PixVerse V6 Extend
  • Hunyuan Video Foley
  • Heygen×3
  • Crystal Upscaler [Video]
  • Lucy 2.1 VTON Realtime
  • LTX Video 2.3 Pro×2
  • DWPose Pose Prediction
  • ID-V2V
  • Bria Video Eraser Erase Mask
  • V1.1 Video to Video Sound Effects
  • Lucy Edit [Pro]
  • Wan VACE Video Edit
  • Heygen Lipsync - Speed
  • Wan 2.2 VACE Fun A14B×4
  • Kling O1 Reference Video to Video [Standard]
  • Workflow Utilities Blend Video
  • Wan 2.1 VACE Long Reframe
  • Topaz Sdr To Hdr Video
  • Lightx×2
  • PixVerse Sound Effects
  • Bernini-R Reference Edit Video
  • ThinkSound×2
  • ID-V2V Relight
  • Topaz Denoise Video
  • LTX Video-0.9.7 13B Distilled×2
  • PixVerse Extend
  • Wan v2.6 Reference to Video
  • Topaz Deblur Video
  • V2.6
  • Scail 2
  • Workflow Utilities Reverse Video
  • Flux 3 Draft Enhance
  • LTX-Video 13B 0.9.8 Distilled×2
  • Flux 3 Action
  • Bernini-R Edit Video
  • Bria Video Eraser×2
  • Hunyuan Video (Video-to-Video)
  • Auto-Captioner
  • Editto
  • Vidu
  • Kandinsky 6.0 VSR×2
  • Controlfoley
  • LTX-2.3 22B×5
  • Krea Wan 14B
  • Marey Realism V1.5×2
  • AMT Interpolation
  • Mirelo SFX
  • Flux 3 Extend Video Draft
  • One To All Animation×2
  • CogVideoX-5B
  • Video Sound Effects Generator
  • AnimateDiff Turbo
  • Cosmos Predict 2.5 2B
  • LTX Video-0.9.5×2
  • AnimateDiff
  • LTX 2.3 22B
  • PixVerse Extend Fast
  • LTX-2.3 22B Distilled×4
  • MAGI-1 (Distilled)
  • Bria's VRMBG 3.0 Realtime

Text to video137 endpoints

  • MiniMax H3 Max Text to Video
  • H3 Max Turbo Text to Video
  • Seedance 2.5 Text to Video
  • Kling Video v3 Text to Video [Pro]
  • Veo 3.1 Fast
  • Seedance 2.0 Text to Video API
  • Kling LipSync Audio-to-Video
  • Kling Video v3 Text to Video [Standard]
  • Wan Text to Video×2
  • MiniMax H3 Text to Video
  • Veo 3.1
  • Kling v2.5 Text to Video
  • Veo3.1 Lite Text to Video
  • Gemini Omni Flash 1.1 Text to Video
  • Seedance 2.0 Fast Text to Video
  • Grok Imagine Video
  • Flux 3 Text to Video
  • Kling Video v2.6 Text to Video
  • Bytedance Seedance V1.5 Pro Text To Video
  • Gemini Omni Flash
  • PixVerse V6 Text To Video
  • Grok Imagine Video 1.5 Lite Text to Video
  • Seedance 2.0 Mini Text to Video
  • Kling O3 Text to Video [Pro]
  • Seedance 2.5 US Text to Video
  • Wan 3.0 Prime
  • Kling Video V3 Standard Turbo Text to Video
  • Grok Imagine Video 1.5 Text to Video
  • Kling O3 Text to Video [Standard]
  • Wan 2.5 Text to Video
  • Kling Video V3 Turbo Pro Text to Video
  • MiniMax Hailuo 02 [Standard] (Text to Video)
  • LTX 2.3 Video Fast
  • Wan-2.2 Text-to-Video A14B
  • Bytedance Seedance V1 Pro Fast Text To Video
  • Flux 3 Text To Video Draft
  • Seedance 1.0 Pro
  • MiniMax Hailuo 2.3 [Standard] (Text to Video)
  • Wan×3
  • Happy Horse
  • Wan v2.6 Text to Video
  • LTX Video 2.3 Pro
  • Ltx 2.5 Text to Video Fast×2
  • LTX Video (preview)
  • Kling Video V3 Text to Video 4K
  • Pika Text to Video (v2.2)
  • Wan v2.2 5B
  • Happy Horse 1.1 Text to Video
  • MiniMax Hailuo 2.3 [Pro] (Text to Video)
  • Luma Ray 3.2 Text to Video
  • Vidu×3
  • PixVerse V5 Text To Video
  • Kling Video
  • Wan-2.1 Text-to-Video
  • Hunyuan Video
  • MiniMax (Hailuo AI) Video 01
  • PixVerse C1 Text To Video
  • LTX Video-0.9.7 13B Distilled
  • Seedance 2.0 US Text to Video
  • PixVerse V4.5 Text To Video
  • PixVerse V5.5 Text To Video
  • MiniMax Hailuo 02 [Pro] (Text to Video)
  • MiniMax H3 Text to Video LoRA
  • Heygen v5 Digital Twin
  • Hunyuan Video V1.5
  • LTX-2.3 22B×2
  • Heygen Video Agent
  • H3 Max VHS
  • LTX-2.3 22B Distilled×2
  • H3 Max 16-bit Pixel
  • CogVideoX-5B
  • MiniMax (Hailuo AI) Video 01 Live
  • Fabric 1.0
  • Kling 1.6×2
  • Kandinsky5 Pro
  • LTX-Video 13B 0.9.8 Distilled
  • Avatars
  • Kandinsky5×2
  • LongCat Video Distilled×2
  • Infinitalk
  • Kandinsky 6.0 Pro
  • Ovi Text to Video
  • LTX Video-0.9.5
  • H3 Max Retro Toon 70s
  • LongCat Video×2
  • Kandinsky 6.0 Lite
  • H3 Max Hand Drawn
  • PixVerse V3.5 Text To Video
  • Cosmos Predict 2.5 2B
  • Vidu Text to Video
  • Wan-2.1 Pro Text-to-Video
  • PixVerse V4.5 Text To Video Fast
  • Wan-2.1 Text-to-Video with LoRAs
  • Krea Wan 14b- Text to Video
  • Kling LipSync Text-to-Video
  • Ltx 2.3 Quality×2
  • PixVerse V4 Text To Video
  • Cosmos Predict 2.5 2B Distilled
  • AnimateDiff
  • PixVerse V5.6 Text To Video
  • AnimateDiff Turbo
  • MAGI-1 (Distilled)
  • Kling 1.0
  • T2V Turbo - Video Crafter
  • MiniMax (Hailuo AI) Video 01 Director
  • H3 Max Low Poly
  • Stable Video Diffusion Turbo
  • Marey Realism V1.5
  • Wan-2.2 Text-to-Video A14B with LoRAs
  • Bernini-R Text to Video
  • Stable Video Diffusion
  • PixVerse V4 Text To Video Fast
  • Avatar X
  • PixVerse V3.5 Text To Video Fast
  • Heygen×3
  • Infinity Star
  • Pika Text to Video (v2.1)
  • Pika Text to Video Turbo (v2)
  • Kling 1.5
  • Avatars Text to Video
  • Boreal
  • H3 Max Director

Audio to video18 endpoints

  • ElevenLabs Dubbing
  • Flashtalk
  • Ltx 2.5 Audio to Video Pro
  • LTX 2.3 Video Pro
  • Wan-2.2 Speech-to-Video 14B
  • Ltx 2.5 Audio to Video Fast
  • PixVerse VibeMV
  • Longcat Single Avatar×2
  • Ltx 2.3 Quality×2
  • LTX-2.3 22B×2
  • LTX-2.3 22B Distilled×2
  • Avatars
  • EchoMimic V3
  • Avatars Audio to Video

Describe video3 endpoints

  • OpenRouter [Video]
  • OpenRouter [Video][Enterprise]
  • Nemotron 3 Nano Omni
Audio & voice143 models

Text to music & sound50 endpoints

  • Elevenlabs Sound Effects V2
  • Elevenlabs Tts Eleven V3
  • ElevenLabs TTS Multilingual v2
  • Elevenlabs Music
  • Elevenlabs Music v2.5
  • Stable Audio 2.5
  • music generator
  • MiniMax Music 3
  • Lyria2
  • Minimax Music 2.6
  • Lyria 3.5
  • Seed Audio 1.0
  • Lyria 3 Pro
  • Minimax Music
  • Stable Audio 3×2
  • ACE Step
  • Stable Audio Open
  • Kokoro TTS
  • Sonilo V1.1 Text to Music
  • V1.1 Text to Sound Effects
  • Sound Effects Generator
  • Elevenlabs
  • ACE Step Prompt To Audio
  • Gemini TTS
  • Lyria3
  • Stable Audio 3 Small SFX Text to Audio
  • MMAudio V2 Text to Audio
  • F5 TTS
  • Stable Audio 3 Small Music Text to Audio
  • Mirelo SFX1.6
  • Minimax Music 2.5
  • Kokoro TTS (British English)
  • MiniMax (Hailuo AI) Music
  • Elevenlabs Music v2
  • MiniMax (Hailuo AI) Music v1.5
  • Kokoro TTS (Spanish)
  • Kokoro TTS (Brazilian Portuguese)
  • Stable Audio 3 Medium Base Text to Audio
  • Kokoro TTS (French)
  • Kokoro TTS (Japanese)
  • Stable Audio 3 Small SFX Base Text to Audio
  • DiffRhythm: Lyrics to Song
  • Zonos-Audio-Clone
  • Kokoro TTS (Italian)
  • CSM-1B
  • Kokoro TTS (Hindi)
  • Ltx 2.3 Quality×2
  • Kokoro TTS (Mandarin Chinese)

Edit audio44 endpoints

  • Demucs
  • Audio Understanding
  • ElevenLabs Audio Isolation
  • ElevenLabs Voice Changer
  • Sam Audio×2
  • Qwen 3 TTS - Clone Voice [1.7B]
  • Kling Video Create Voice
  • FFmpeg API [Merge Audios]
  • DeepFilterNet 3
  • ACE Step Audio To Audio
  • VEED Clean Audio
  • Stable Audio 2.5
  • Stable Audio 3 Medium Audio to Audio
  • ACE Step Audio Inpaint
  • Workflow Utilities Audio Compressor
  • Qwen 3 TTS - Clone Voice [0.6B]
  • ACE Step Audio Outpaint
  • Stable Audio 3 Medium Audio Outpainting
  • Stable Audio 3 Medium Base Audio to Audio
  • Tada
  • Stable Audio 3 Medium Audio Inpainting
  • Stable Audio 3×2
  • Stable Audio 25
  • Personaplex×2
  • Stable Audio 3 Small Music Base Audio to Audio
  • Stable Audio 3 Medium Base Audio Inpainting
  • Stable Audio 3 Small Music Audio Inpainting
  • Dia Tts
  • Stable Audio 3 Small Music Base Audio Inpainting
  • Stable Audio 3 Medium Base Audio Outpainting
  • Stable Audio 3 Small Music Audio Outpainting
  • Stable Audio 3 Small SFX Audio Outpainting
  • Tada TTS 1B
  • Stable Audio 3 Small SFX Audio Inpainting
  • Stable Audio 3 Small Music Base Audio Outpainting
  • Stable Audio 3 Small SFX Base Audio to Audio
  • Mirelo SFX1.6×2
  • Stable Audio 3 Small SFX Base Audio Outpainting
  • Stable Audio 3 Small SFX Base Audio Inpainting
  • Workflow Utilities Impulse Response

Text to speech38 endpoints

  • Eleven v4
  • MiniMax Speech-02 HD
  • MiniMax Speech 2.8 [HD]
  • Gemini 3.8 Flash TTS
  • ElevenLabs TTS Turbo v2.5
  • Gemini 3.1 Flash Tts
  • MiniMax Voice Cloning
  • Eleven v4 Turbo
  • Qwen 3 TTS - Text to Speech [1.7B]
  • MiniMax Speech 2.8 [Turbo]
  • Inworld TTS-1.5 Max
  • MiniMax Speech-02 Turbo
  • MiniMax Speech 2.6 [HD]
  • Chatterbox×2
  • MiniMax Voice Design
  • xAI Text to Speech
  • Qwen 3 TTS - Voice Design [1.7B]
  • Gemini 3.8 Flash Lite TTS
  • Index TTS 2.0
  • Chatterboxhd
  • Bytedance Seed Speech Text to Speech
  • Zonos2 Text to Speech
  • VibeVoice 7B
  • MiniMax Speech 2.6 [Turbo]
  • Qwen Audio 3.0 TTS (Flash)
  • Maya1
  • Minimax×2
  • Kling TTS
  • Orpheus TTS
  • Dia
  • Qwen 3 TTS - Text to Speech [0.6B]
  • VibeVoice 1.5B
  • Async Text to Speech Pro V1.0
  • Vibevoice
  • Maya×2

Speech to text11 endpoints

  • ElevenLabs Speech to Text - Scribe V2
  • Wizper (Whisper v3 -- fal.ai edition)
  • ElevenLabs Speech to Text
  • Elevenlabs - Forced Alignment
  • Cohere Transcribe
  • Nemotron Asr Multilingual
  • Speech-to-Text×3
  • Speech-To-text
  • Pipecat's Smart Turn model

Video to audio6 endpoints

  • V1.1 Video to Sound Effects
  • V1.1
  • Kling Video
  • Mirelo SFX V1.5
  • Sam Audio
  • Mirelo SFX

Voice to voice4 endpoints

  • Chatterboxhd
  • Chatterbox
  • Grok Voice×2

Describe audio2 endpoints

  • Nemotron 3 Nano Omni
  • Silero VAD
3D55 models

Image to 3D42 endpoints

  • Hunyuan 3D Pro Image to 3D
  • Trellis 2×2
  • Tripo H3.1 Image to 3D
  • Trellis×2
  • Hunyuan3d V3×2
  • Meshy 7.1 Image to 3D
  • Hyper3D - Rodin V2.5 - Image to 3D
  • Tripo H3.1 Multiview to 3D
  • Meshy 7.1 Multi Image to 3D
  • Tripo P2 Image to 3D
  • Sam 3×2
  • Tripo3D×2
  • Meshy 6
  • Hyper3D Rodin
  • V7 Image to 3D
  • Hyper3d
  • Hyper3D - Rodin V2.5 - Image to 3D - Fast
  • Hunyuan3D×6
  • Hunyuan 3D Rapid Image to 3D
  • Triposplat
  • Meshy 6 Preview
  • Hi3D Image to 3D×2
  • Hi3D Multiview to 3D×2
  • V7 Multi Image to 3D
  • Pixal3d
  • Tripo P1 Image to 3D
  • Hunyuan World
  • ReconViaGen 0.5
  • TRELLIS.2 LoRA Inference
  • TripoSR

Text to 3D14 endpoints

  • Tripo H3.1 Text to 3D
  • Hunyuan Motion [1B]
  • Hunyuan 3D Pro Text to 3D
  • Meshy 6
  • Meshy 7.1 Text to 3D
  • Tripo P2 Text to 3D
  • Hyper3D - Rodin V2.5 - Text to 3D
  • Hyper3D - Rodin V2.5 - Text to 3D - Fast
  • V7 Text to 3D
  • Hunyuan 3d
  • Meshy 6 Preview
  • Hunyuan3d V3
  • Tripo P1 Text to 3D
  • Hunyuan Motion [0.46B]

Edit 3D11 endpoints

  • Meshy Rigging Multi Animation
  • Meshy Rigging
  • Hunyuan 3D Smart Topology
  • Hunyuan 3D Part Splitter
  • Tripo3D Segment
  • Tripo3D Remesh
  • Hi3D 3D Part Splitter
  • Hi3D Texture
  • Sam 3
  • Hi3D 3D to Multicolor
  • Meshy 6 Lite Retexture
Other19 models

Language models8 endpoints

  • OpenRouter Chat Completions [OpenAI Compatible]
  • OpenRouter
  • OpenRouter Responses [OpenAI Compatible]
  • OpenRouter Embeddings [OpenAI Compatible]
  • OpenRouter [Enterprise]
  • Bytedance Seed V2 Mini
  • Video Prompt Generator
  • Nemotron 3 Nano Omni

Tools & metadata6 endpoints

  • FFmpeg API Metadata
  • Ffmpeg Api
  • FFmpeg API Waveform
  • Omnilottie×3

Other3 endpoints

  • OpenRouter [Audio]
  • Seedance 2.5
  • Workflow Utilities Interleave Video

Training2 endpoints

  • Recraft V4 Styles Create Style
  • Recraft V4 Styles Pro Create Style

text-to-text1 endpoint

  • Router

Workflow1 endpoint

  • Workflow Utilities Pick Image By Index

Versions and availability change constantly; the catalogue is updated regularly. The mapping to use cases follows the models’ names and descriptions and is a guide, not a guarantee.

OMVIN by flow office

All of it. In one interface.

No subscription jungle, no switching tools: you describe what you need and name the model — or ask OMVIN for a recommendation. OMVIN calls it and delivers the result — for your business, practice, shop or at home.

Get started Discover OMVIN