AI model directory

Text to image · Image to image

from 21 tokens per image

Black Forest Labs Flux 2 Pro

Text to image · Image to image

from 10 tokens per image

Black Forest Labs Flux 3 Klein

Text to image · Image to image

from 3.2 tokens per image

Claude Haiku 5.5

Anthropic

Text conversation · Model response

Claude Opus 5

Anthropic

Text conversation · Model response

Claude Opus 5.5

Anthropic

Text conversation · Model response

DeepSeek V4.1 Flash

DeepSeek

Text conversation · Cached input · Model response

ElevenLabs Audio Isolation

audio isolation

from 0.4 tokens per second

ElevenLabs Sound Effect V2

sound effects

from 0.48 tokens per second

ElevenLabs Text To Speech

from 12 tokens per 1,000 characters

Text to speech

ElevenLabs V3

from 28 tokens per 1,000 characters

text to dialogue

Gemini 3.1 Flash TTS

from 12 tokens per 1,000 characters

Text to speech

Gemini 3.7 Flash

Text conversation · Model response

Gemini 3.8 Flash

Text conversation · Model response

Gemini 3.8 Flash TTS

from 12 tokens per 1,000 characters

Text to speech

Gemini 3.8 Flash-Lite TTS

from 8 tokens per 1,000 characters

Text to speech

Gemini 4 Argon

Text conversation · Model response

Gemini Omni 1.1 Flash

Text to video · Video to video

from 126 tokens per video

Gemini Omni Video

Text to video · Video to video

from 110 tokens per video

Google Nano Banana

Text to image

Google Nano Banana 2

image

Google Nano Banana 2 Lite

image

Google Nano Banana 2.1

Text to image · Image to image

Google Nano Banana Edit

Image to image

Google Nano Banana Pro

image

from 25 tokens per image

Google Veo 3.1 fast

Reference to video · Text to video · Image to video

from 110 tokens per video

Google Veo 3.1 lite

Reference to video · Text to video · Image to video

from 60 tokens per video

Google Veo 3.1 quality

Text to video · Image to video

from 500 tokens per video

GPT 5.6 Luna

Text conversation · Model response

GPT 5.6 Sol

Text conversation · Model response

GPT 5.6 Terra

Text conversation · Model response

GPT 6 Astra

Text conversation · Cached input · text cache write · Model response

GPT 6.1 Sol

Text conversation · Cached input · text cache write · Model response

GPT Image 1.5

Image to image · Text to image

from 13.6 tokens per image

GPT Image 2

Image to image · Text to image

GPT Image 2.5 Flare

Text to image · Image to image

from 12 tokens per image

GPT Image 2.5 Sunburst

Text to image · Image to image

from 12 tokens per image

Grok 4.5

Text conversation · Model response

Grok 4.6

Text conversation · Cached input · Model response

Grok 4.7

Text conversation · Cached input · Model response

Grok Imagine

Image to image · Text to image

Grok Imagine

Image to video · Text to video

from 3.2 tokens per second

Grok Imagine Image 2.0

Text to image · Image to image

Grok Imagine Video 1.5 Preview

Image to video

from 3.2 tokens per second

Hailuo 2.3

Image to video

from 60 tokens per video

HappyHorse 1.0

from 56 tokens per second

Reference to video · Video editing · Image to video · Text to video

HappyHorse 1.1

from 66 tokens per second

Image to video · Text to video · Reference to video

Kling 2.6 Motion Control

from 20 tokens per second

Video to video

Kling 3.0

from 17 tokens per second

video

Kling 3.0 Motion Control

from 30 tokens per second

Video to video

Kling 3.0 Turbo

from 28 tokens per second

Image to video · Text to video

Kling 4.0

from 19 tokens per second

Text to video · Image to video · Video to video

Kling O3

from 28 tokens per second

Text to video · Image to video · Reference to video · Video to video

MeiGen-AI InfiniteTalk

request

from 6 tokens per second

MiniMax H3

Text to video · Image to video · Reference to video

from 22.5 tokens per second

OmniHuman 2.0

from 21 tokens per second

request

PixVerse V6

Text to video · Image to video · transition · Reference to video · extend

from 5 tokens per second

Qwen Image 3

Alibaba

Text to image · Image to image

from 6 tokens per image

Qwen Image 3 Pro

Alibaba

Text to image · Image to image

Qwen Z-Image

Alibaba

Text to image

from 1.6 tokens per image

Qwen2 Image Edit

Image to image · Text to image

from 11.2 tokens per image

Recraft Crisp Upscale

Image to image

from 1 token per image

Recraft Remove Background

Image to image

from 2 tokens per image

Runway

Text to video · Image to video

from 24 tokens per video

Seedance 1.5 Pro

video

from 3.5 tokens per second

Seedance 2

from 23 tokens per second

Text to video · Video to video

Seedance 2 Fast

from 17 tokens per second

Text to video · Video to video

seedance 2 mini

from 11 tokens per second

Text to video · Video to video · Reference to video

Seedance 2.5

from 19 tokens per second

Text to video · Video to video

Seedream 4.5

Image to image · Text to image

from 13 tokens per image

Seedream 5.0 Flash

Text to image · Image to image

from 6.48 tokens per image

Seedream 5.0 Lite

Image to image · Text to image

Seedream 5.0 Pro

Text to image · Image to image

from 24 tokens per image

from 0 tokens per request

Suno

music style boost · convert to wav format · generate lyrics · timestamped lyrics · vocal separation · mashup · upload and cover audio · upload and extend audio · add instrumental · generate music · extend music · add vocals · create music video · sound effects · replace music section · multi stem separation · generate voice · generate persona · advanced stem separation

Topaz Image Upscaler

Topaz Labs

Image upscale

from 20 tokens per image

from 16 tokens per second

Topaz Video Upscaler

Topaz Labs

Upscale

WAN 2.5

Text to video · Image to video

from 120 tokens per video

WAN 2.6

Video to video · Image to video · Text to video

from 140 tokens per video

WAN 2.7 Image

image

from 9.6 tokens per image

WAN 2.7 Image Pro

image

from 24 tokens per image

WAN 2.7 Video

from 32 tokens per second

Video editing · Reference to video · Image to video · Text to video

Wan 3.0

from 16 tokens per second

Text to video · Video to video

Wan 3.0 Prime

Text to video · Video to video

from 24.48 tokens per second