AI Models

57+ models for text, image, video, voice, and audio generation. All accessible through a single API endpoint.

ByteDance Video

Seedance 2.0 Reference

Multi-reference video with up to 9 images, 3 videos, and 3 audio files

View details →
OpenAI Text

GPT-5.5

Frontier intelligence for coding and professional work

View details →
OpenAI Text

GPT-5.4

Top-tier reasoning with up to 272K context

View details →
OpenAI Text

GPT-5.4 Pro

Enhanced GPT-5.4 with extended capabilities

View details →
OpenAI Text

GPT-5

Capable general-purpose model with strong reasoning

View details →
OpenAI Text

GPT-5 Mini

Fast and affordable for everyday tasks

View details →
OpenAI Text

GPT-5.3 Codex

Code-specialized model with 400K context

View details →
OpenAI Text

GPT-5 Nano

Most affordable model for simple, high-volume tasks

View details →
OpenAI Text

GPT-5.4 Mini

Fast, affordable GPT-5.4 variant

View details →
Anthropic Text

Claude Opus 4.7

Step-change agentic coding with 1M token context

View details →
Anthropic Text

Claude Opus 4.6

Most capable model with 1M token context

View details →
Anthropic Text

Claude Sonnet 4.6

Balanced reasoning and coding at lower cost

View details →
Anthropic Text

Claude Haiku 4.5

Fastest model, optimized for speed and cost

View details →
Google Text

Gemini 3.1 Pro

Most capable multimodal model with image output

View details →
Google Text

Gemini 3 Flash

Fast multimodal model with audio input

View details →
Google Text

Gemini 3.1 Flash Lite

Lightest model, optimized for speed and cost

View details →
OpenAI Image

GPT Image 2

State-of-the-art image generation and editing

View details →
xAI Text

Grok 4.1 Fast Reasoning

Fast reasoning with massive 2M context window

View details →
xAI Text

Grok 4.1 Fast

Speed-optimized non-reasoning for high-throughput tasks

View details →
xAI Text

Grok 4.2 Multi-Agent

Collaborative, parallel research tasks

View details →
xAI Text

Grok 4.2 Reasoning

Deep reasoning for complex analytical tasks

View details →
xAI Text

Grok 4.2

Latest general-purpose model with broad knowledge

View details →
xAI Image

Grok Imagine

Creative and expressive image generation

View details →
xAI Image

Grok Imagine Pro

Premium image generation with higher quality

View details →
Google Image

Nano Banana 2

Creative and artistic image generation via Gemini

View details →
Google Image

Nano Banana Pro

Premium image generation via Gemini

View details →
Recraft Image

Recraft V4

Fast, affordable image generation

View details →
Recraft Image

Recraft V4 Pro

Premium image generation at 2x resolution

View details →
Recraft Image

Recraft V4 Vector

SVG vector image generation from text

View details →
Recraft Image

Recraft V4 Pro Vector

Premium SVG vector generation

View details →
Google Video

Veo 3.1

High-quality video from text via Gemini

View details →
Google Video

Veo 3.1 Fast

Fast video generation at lower cost

View details →
xAI Video

Grok Imagine Video

Short video generation from text

View details →
Kling Video

Kling v3 Pro

High-quality text-to-video via Fal.ai

View details →
Kling Video

Kling v2.6 Pro

Reliable video generation via Fal.ai

View details →
Kling Video

Kling v2.5 Turbo

Fast turbo video generation

View details →
Kling Video

Kling v3 Pro I2V

High-quality image-to-video via Fal.ai

View details →
ByteDance Video

Seedance v1 Fast

Fast creative videos via Fal.ai

View details →
Kling Video

Kling v2.6 Pro I2V

Image-to-video with audio via Fal.ai

View details →
PixVerse Video

PixVerse v5.5

Stylized video generation via Fal.ai

View details →
Deepgram Voice

Aura 2

Natural, expressive text-to-speech

View details →
Kling Video

Kling v2.5 Turbo I2V

Fast image-to-video generation

View details →
Google Audio

Lyria 3 Clip Preview

30-second music clips from text or images

View details →
xAI Voice

Grok TTS

Text-to-speech with multiple voices

View details →
Kling Video

Kling Avatar 2.0 Pro

Lip-synced talking avatars from image + audio

View details →
Google Audio

Lyria 3 Pro Preview

Full songs with lyrics, vocals, and structure

View details →
ByteDance Video

Seedance v1 Fast I2V

Image-to-video via Fal.ai

View details →
GenX Pro Voice

GenX LM Voice v1

Native voice cloning from reference audio

View details →
PixVerse Video

PixVerse v5.5 I2V

Stylized image-to-video via Fal.ai

View details →
PixVerse Video

PixVerse v6

Cinematic text-to-video with style presets and flexible duration

View details →
PixVerse Video

PixVerse v6 I2V

Animate images into cinematic video with style presets

View details →
ByteDance Video

Seedance 2.0

High-quality T2V with native audio and physically accurate motion

View details →
ByteDance Video

Seedance 2.0 I2V

Animate images with end-frame control and native audio

View details →
GenX Text

GenX LM Pro v1 TL

Translation model for 9 languages

View details →
GenX Image

GenX LM Pro v1 IMG

High-quality generation on dedicated GPUs

View details →
GenX Image

GenX LM Pro v1 IMG Fast

Quick generation on dedicated GPUs

View details →
GenX transcription

GenX LM Pro v1 TR

Audio transcription on dedicated GPUs

View details →

Start Building Today

500 free credits. No credit card required. One API for all models.