Skip to main content

Models

Explore our collection of AI models for image, video, and audio generation.

Image Generation

Create stunning images from text prompts or transform existing images.

Nano Banana

Fast image generation for rapid prototyping

Nano Banana Pro

Higher resolution output with more control

Flux-2

High-quality images with Pro and Flex modes

Flux Kontext

Context-aware image generation and editing

GPT-Image-1

OpenAI-powered image generation with variants

Midjourney

Premium artistic style with flexible controls

Seedream 4.5

Photorealistic image synthesis at high resolution

Seedream 5.0

Next-gen image generation with web search, editing, and reasoning

Video Generation

Generate videos from text descriptions or animate still images.

Sora 2

OpenAI’s advanced text-to-video and image-to-video

Sora 2 Pro

High-quality video generation with resolution control

Veo 3.1

Google’s high-fidelity video generation

Wan 2.5

Fast video generation with flexible durations

Audio Generation

Create music, sound effects, and audio content.

Suno V5

AI music generation with vocals and instrumentals

LLM Models

Build assistants, agents, and reasoning workflows with official LLM APIs.

Claude API

Official Anthropic /v1/messages endpoint on APIXO LLM gateway

OpenAI Responses API

Official OpenAI /v1/responses endpoint for non-stream and stream calls

Gemini API

Official Google /v1beta/models/{model}:generateContent and stream endpoints

Pricing

Pricing is maintained on the Pricing page. For the latest model prices and strategy differences, always refer to that page.

Choosing a Model

For rapid prototyping: Start with Nano Banana or Wan 2.5 for fast iteration. For production quality: Use Flux-2 Pro or Midjourney for images, Sora 2 for videos. For photorealism: Seedream 4.5 excels at clean, realistic imagery.