Every model in one catalog

from 16 ⚡Text to videoImage to video3–15 s

Text to video, Image to video, Motion transfer

Kling 3.0 TurboNEW

from 14 ⚡Text to videoImage to video3–15 s

Text to video, Image to video

Kling 3.0 OmniNEW

from 11 ⚡Text to videoImage to video3–15 s

Text to video, Image to video, From references, Video edit

Kling Motion ControlNEW

Motion transfer

from 26 ⚡Motion transfer

Kling 2.6 Pro

from 14 ⚡Text to videoImage to video5–10 s

Text to video, Image to video, Motion transfer

Kling 2.5 Turbo

from 11 ⚡Text to videoImage to video5–10 s

Text to video, Image to video

Kling 2.1 Master

from 42 ⚡Text to videoImage to video5–10 s

Text to video, Image to video

Kling 2.1 Pro

from 13 ⚡Image to video5–10 s

Image to video

Kling 2.1 Standard

from 7 ⚡Image to video5–10 s

Image to video

Wan 3.0NEW

from 6 ⚡Text to videoImage to video3–15 s

Text to video, Image to video, From references

Wan 3.0 PrimeNEW

from 10 ⚡Text to videoImage to video3–15 s

Text to video, Image to video, From references

Veo 3.1NEW

Veo · Video model

Image to video, Standard (from text), Fast (from text), Fast (from image)

from 16 ⚡Image to videoStandard (from text)4–8 s

Veo 3.1 LiteNEW

Veo · Video model

Image to video, Standard (from text)

from 8 ⚡Image to videoStandard (from text)4–8 s

Veo 3.0

Veo · Video model

Image to video, Standard (from text), Fast (from text), Fast (from image)

from 16 ⚡Image to videoStandard (from text)4–8 s

Seedance 2.5NEW

from 29 ⚡Text to videoImage to video4–30 s

Text to video, Image to video, From references

Seedance 2.0

from 20 ⚡Text to videoImage to video4–15 s

Text to video, Image to video, From references

Seedance 2.0 Fast

from 12 ⚡Text to videoImage to video4–15 s

Text to video, Image to video, From references

Seedance 2.0 Mini

from 4 ⚡Text to videoImage to video4–15 s

Text to video, Image to video, From references

Seedance v1.5 Pro

from 2 ⚡Text to videoImage to video4–12 s

Text to video, Image to video

MiniMax H3NEW

Minimax · Video model

Text to video, Image to video, From references

from 23 ⚡Text to videoImage to video4–15 s

Hailuo 2.3 Pro

from 14 ⚡Image to video6–10 s

Image to video

Hailuo 2.3 Standard

from 8 ⚡Image to video6–10 s

Image to video

Hailuo 02 Pro

from 15 ⚡Text to videoImage to video

Text to video, Image to video

PixVerse V6NEW

PixVerse · Video model

Text to video, Image to video, From references, Transition between frames, Extend a clip

from 1 ⚡Text to videoImage to video1–15 s

Hailuo 02

from 3 ⚡Text to videoImage to video6–10 s

Text to video, Image to video

Grok Imagine Video 1.5NEW

Grok · Video model

Text to video, Image to video

from 4 ⚡Text to videoImage to video6–15 s

Grok Imagine 1.5 PreviewNEW

Grok · Video model

Text to video, Image to video

from 1 ⚡Text to videoImage to video1–15 s

Gemini Omni 1.1 FlashNEW

Gemini · Video model

Text to video, Image to video

from 16 ⚡Text to videoImage to video4–10 s

Gemini OmniNEW

Gemini · Video model

Text to video, Image to video

from 16 ⚡Text to videoImage to video4–10 s

Wan 2.7

from 8 ⚡Text to videoImage to video2–15 s

Text to video, Image to video, From references, Video edit

Wan 2.6FREE

from 18 ⚡Text to videoImage to video5–15 s

Text to video, Image to video, From references

Wan 2.6 Flash

from 5 ⚡Image to videoFrom references5–15 s

Image to video, From references

Wan 2.5

from 16 ⚡Text to videoImage to video5–10 s

Text to video, Image to video

Wan 2.2 Turbo

from 10 ⚡Text to videoImage to video

Text to video, Image to video

Wan 2.2 Animate

from 8 ⚡Animate a photo from a videoReplace a character in a video

Animate a photo from a video, Replace a character in a video

HappyHorse 1.1NEW

HappyHorse · Video model

Text to video, Image to video, From references

from 18 ⚡Text to videoImage to video3–15 s

HappyHorse 1.0

HappyHorse · Video model

Text to video, Image to video, From references, Video edit

from 22 ⚡Text to videoImage to video3–15 s

Vidu Q4NEW

Vidu · Video model

Image to video, From references

from 6 ⚡Image to videoFrom references3–16 s

Runway Gen-4NEW

Runway · Video model

Text to video, Image to video, Video edit

from 4 ⚡Text to videoImage to video5–10 s

Grok Imagine ToolsNEW

Grok · Studio tool

Extend a clip, Clip upscale

from 5 ⚡Extend a clipClip upscale

Seedance 2.5 FinalizeNEW

Seedance · Studio tool

Finish a draft to 1080p

from 82 ⚡Finish a draft to 1080p

Kling AvatarNEW

from 10 ⚡Talking avatar (lip-sync)

Talking avatar (lip-sync)

Kling Avatar ProHD

from 21 ⚡Talking avatar (lip-sync)

Talking avatar (lip-sync)

InfiniteTalk

from 4 ⚡Talking avatar (lip-sync)

Talking avatar (lip-sync)

Wan Speech

from 16 ⚡Talking avatar (lip-sync)

Talking avatar (lip-sync)

OmniHuman 1.5NEW

from 35 ⚡Talking avatar (lip-sync)

Talking avatar (lip-sync)

Lipsync VideoNEW

from 10 ⚡Talking avatar (lip-sync)

Talking avatar (lip-sync)

Image models 26

FLUX 2 MaxPRO

Black Forest Labs · Image model

standard · HD

from 1 ⚡up to 8 images

Nano Banana 2.1NEW

standard · HD · Ultra · 4K

Nano Banana ProTOP

from 5 ⚡Edit an imageup to 8 images

standard · HD · Ultra · 4K

Nano Banana 2

from 2 ⚡Edit an imageup to 10 images

standard · HD · Ultra · 4K

Nano Banana 2 Lite

standard

Nano Banana

standard

from 1 ⚡Edit an imageup to 5 images

Grok Imagine 2NEW

xAI · Image model

standard

Grok Imagine

xAI · Image model

standard

from 1 ⚡Edit an imageup to 5 images

GPT Image 2.5NEW

from 2 ⚡Edit an imageup to 16 images

standard · HD · Ultra

GPT Image 2.5 SunburstNEW

from 2 ⚡Edit an imageup to 16 images

standard · HD · Ultra

GPT Image 2

from 2 ⚡Edit an imageup to 16 images

standard · HD · Ultra

Ideogram V3NEW

Ideogram · Image model

standard · HD · Ultra

from 1 ⚡Edit an imageup to 1 images

Ideogram CharacterNEW

Ideogram · Image model

standard · HD · Ultra

from 3 ⚡Edit an imageup to 1 images

Z-ImageCHEAP

Alibaba (Tongyi) · Image model

standard

from 1 ⚡

Seedream 5.0 ProNEW

from 2 ⚡Edit an imageup to 10 images

standard · HD

Seedream 5.0 LiteNEW

from 1 ⚡Edit an imageup to 14 images

standard · HD · Ultra · 4K

FLUX 2 FlexNEW

Black Forest Labs · Image model

standard · HD

from 4 ⚡up to 8 images

GPT Image 1.5

from 1 ⚡Edit an imageup to 16 images

standard · HD

Seedream 5.0 FlashFAST

standard · HD

Qwen Image 3 ProNEW

from 2 ⚡Edit an imageup to 3 images

standard · HD

Qwen Image 3

from 1 ⚡Edit an imageup to 3 images

standard · HD

Seedream 4.5

from 2 ⚡Edit an imageup to 14 images

standard · HD · Ultra · 4K

Qwen Image 2.1

standard · HD

Qwen Image 2

from 1 ⚡Edit an imageup to 1 images

standard

Wan 2.7 Image ProPRO

from 3 ⚡Edit an imageup to 9 images

standard · HD · Ultra · 4K

Wan 2.7 ImageNEW

from 1 ⚡Edit an imageup to 9 images

standard · HD

Voice and music 7

ElevenLabs Multilingual v2DEFAULT

ElevenLabs · Text to speech

Even-toned and the most universal across languages. Russian works in every voice.

8 ⚡ / 1000

ElevenLabs v3 DialogueEXPRESSIVE

ElevenLabs · Text to speech

Emotions and several voices in one scene. Paid voices only.

8 ⚡ / 1000

Suno generates music and sound effects in the Studio. Versions V6, V6 Mini and V6 Wild are available.

from 4 ⚡V6SFX

Main chat models 238

The chat offers 238 text models. The main ones are below; the full list with search and filters is on its own page.

Auto

GIBRID.AI · Chat model

Picks the right model per question — cheap for simple, strong for hard.

imagestoolsthinking

GPT-5.3 Codex

GPT-5.3 Codex — the freshest Codex.

Claude Haiku 4.5

Claude Haiku 4.5 — fastest Claude 4.x.

Gemini 3.1 Pro Preview

Google · Chat model

Gemini 3.1 Pro — Google flagship, vision + long context.

Grok-4.1 Fast Reasoning

xAI · Chat model

Grok-4.1 Fast Reasoning — fast 4.1 reasoning.

Grok 4.6

xAI · Chat model

≈ 1 ⚡ per messagethinkingtoolsweb search

DeepSeek v4 Pro

DeepSeek · Chat model

DeepSeek v4 Pro — DeepSeek flagship.

Llama-4 Maverick

Meta · Chat model

Llama-4 Maverick — fresh Meta Llama.

≈ 1 ⚡ per messageimageslong contexttools

GLM 5.3

Z.ai · Chat model

Zai GLM 5.3 — reasoning · long context · tool-calling · web-search

≈ 1 ⚡ per messagethinkinglong contexttools

Command A

Cohere · Chat model

Command A — Cohere flagship.

≈ 1 ⚡ per messagelong contexttoolsweb search

Claude Sonnet 5

Anthropic Claude Sonnet 5 — vision · reasoning · tool-calling · long context · web-search

Claude Opus 5

≈ 2 ⚡ per messagethinkingimageslong context

Anthropic Claude Opus 5 — reasoning · vision · long context · tool-calling · web-search

Claude Fable 5.1

≈ 5 ⚡ per messageimagesthinkingtools

Gemini 3.8 Flash

Google · Chat model

≈ 1 ⚡ per messagefastimagesthinking

Qwen 3.8 Max

Alibaba (Qwen) · Chat model

≈ 1 ⚡ per messagethinkingtoolslong context

DeepSeek V4 Pro 0813

DeepSeek · Chat model

This is the 8/13 updated weights version of DeepSeek V4 Pro.

Kimi K3 Fast

Moonshot AI · Chat model

Fast version of Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.

≈ 2 ⚡ per messagefastimagesthinking

MiniMax M3

MiniMax · Chat model

Muse Spark 1.3

Meta · Chat model

Mistral Medium 3.5

Mistral AI · Chat model

Mistral's frontier-class multimodal model optimized for agentic and coding use cases.

GPT-5.6 Terra

Openai GPT-5.6 Terra — reasoning · vision · long context · tool-calling · web-search

GPT-5.6 Luna

Openai GPT-5.6 Luna — reasoning · vision · long context · tool-calling · web-search

Alibaba (Qwen) · Chat model

Qwen 3.8 Max Prime

Alibaba Qwen 3.8 Max Prime — reasoning · vision · long context · tool-calling · web-search

≈ 2 ⚡ per messagethinkingimageslong context

Claude Haiku 5.5

Anthropic Claude Haiku 5.5 — reasoning · vision · long context · tool-calling · web-search

Claude Opus 5.5

≈ 2 ⚡ per messagethinkingfastimages

Anthropic Claude Opus 5.5 — reasoning · fast · vision · long context · tool-calling · web-search

Claude Sonnet 5.5

Anthropic Claude Sonnet 5.5 — reasoning · vision · long context · tool-calling · web-search

DeepSeek V4.1 Flash

DeepSeek · Chat model

Deepseek DeepSeek V4.1 Flash — reasoning · fast · vision · long context · tool-calling · web-search

Mistral Large 4

Mistral AI · Chat model

Mistral Mistral Large 4 — reasoning · vision · long context · tool-calling · web-search

GPT-6 Astra

≈ 5 ⚡ per messagethinkingfastimages

Openai GPT-6 Astra — reasoning · fast · vision · long context · tool-calling · web-search

GPT-6 Luna

Openai GPT-6 Luna — reasoning · fast · vision · long context · tool-calling · web-search

GPT-6.1 Sol

Openai GPT-6.1 Sol — reasoning · fast · vision · long context · tool-calling · web-search

Grok 4.7

xAI · Chat model

Xai Grok 4.7 — reasoning · vision · long context · tool-calling · web-search