> ## Documentation Index
> Fetch the complete documentation index at: https://apixo.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Multimodal AI Models
> Browse APIXO image, video, audio, chat, and utility APIs from one model catalog
Browse APIXO APIs by output type or provider family. Image, video, and audio models generally use the asynchronous Generation API workflow. Chat models use Claude, OpenAI, or Gemini-compatible request formats, while utility APIs document their own task requirements.
## Base URL
```text theme={null}
https://api.apixo.ai/api/v1
```
## Request flow
| Step | Endpoint | Purpose |
| -------- | ------------------------------------- | ------------------------------------------- |
| 1 | `POST /generateTask/{model}` | Submit a generation task |
| 2 | `GET /statusTask/{model}?taskId={id}` | Poll task status and retrieve results |
| Optional | `callback_url` in the request body | Receive webhook delivery instead of polling |
## Start here
Submit an image, video, or audio generation task.
Poll for task progress, final results, and failures.
Receive task completion callbacks in production.
Compare common request fields across models.
## Model categories
Generate images, edit references, upscale, and create variations.
Generate videos from text, images, first and last frames, or references.
Generate music, speech, and voice outputs.
Use Claude, OpenAI, or Gemini-compatible APIs and switch models by ID.
Optimize prompts and browse APIs outside the primary media categories.
## Browse by provider
| Category | Provider or family | Models |
| -------- | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Image | Google | [Nano Banana](/docs/models/image/nano-banana), [Nano Banana Pro](/docs/models/image/nano-banana-pro), [Nano Banana 2](/docs/models/image/nano-banana-2) |
| Image | OpenAI | [GPT Image 1](/docs/models/image/gpt-image-1), [GPT Image 2](/docs/models/image/gpt-image-2) |
| Image | Z-Image | [Z-Image LoRA](/docs/models/image/z-image-lora) |
| Image | xAI | [Grok Image](/docs/models/image/grok-image) |
| Image | Black Forest Labs | [Flux 2](/docs/models/image/flux-2), [Flux Kontext](/docs/models/image/flux-kontext) |
| Image | Midjourney | [Midjourney](/docs/models/image/midjourney) |
| Image | MiniMax | [MiniMax Image 01](/docs/models/image/minimax-image-01) |
| Image | Runway | [Runway Gen4 Image](/docs/models/image/runway-gen4-image), [Runway Gen4 Image Turbo](/docs/models/image/runway-gen4-image-turbo) |
| Image | ByteDance | [Seedream 4.0](/docs/models/image/seedream-4-0), [Seedream 4.5](/docs/models/image/seedream-4-5), [Seedream 5.0](/docs/models/image/seedream-5-0), [Seedream 5.0 Pro](/docs/models/image/seedream-5-0-pro) |
| Image | Alibaba | [Qwen Image](/docs/models/image/qwen), [Qwen 2 Image](/docs/models/image/qwen-2-image), [Qwen Image Edit LoRA](/docs/models/image/qwen-image-edit-lora), [Wan 2.5 Image](/docs/models/image/wan-2-5-image), [Wan 2.6 Image](/docs/models/image/wan-2-6-image), [Wan 2.7 Image](/docs/models/image/wan-2-7-image) |
| Image | Image utilities | [Face Swap LoRA](/docs/models/image/face-swap-lora), [Head Swap LoRA](/docs/models/image/head-swap-lora), [Image Upscaler](/docs/models/image/image-upscaler), [Image Watermark Remover](/docs/models/image/image-watermark-remover) |
| Video | OpenAI | [Sora 2](/docs/models/video/sora-2), [Sora 2 Pro](/docs/models/video/sora-2-pro) |
| Video | Runway | [Runway Gen4 Video Turbo](/docs/models/video/runway-gen4-video-turbo) |
| Video | Google | [Veo 3.1](/docs/models/video/veo-3-1), [Gemini Omni](/docs/models/video/gemini-omni) |
| Video | xAI | [Grok Video](/docs/models/video/grok-video) |
| Video | Alibaba | [Wan 2.2 Animate](/docs/models/video/wan-2-2-animate), [Wan Animate LoRA](/docs/models/video/wan-animate-lora), [Wan 2.2 Video LoRA](/docs/models/video/wan-2-2-video-lora), [Wan 2.5 Video](/docs/models/video/wan-2-5-video), [Wan 2.6 Video](/docs/models/video/wan-2-6-video), [Wan 2.7 Video](/docs/models/video/wan-2-7-video), [Wan 2.7 Video LoRA](/docs/models/video/wan-2-7-video-lora), [HappyHorse](/docs/models/video/happyhorse) |
| Video | ByteDance | [Seedance 1.5 Pro](/docs/models/video/seedance-1-5-pro), [Seedance 2.0](/docs/models/video/seedance-2-0), [Seedance 2.0 Fast](/docs/models/video/seedance-2-0-fast), [Seedance 2.0 Mini](/docs/models/video/seedance-2-0-mini) |
| Video | Kuaishou | [Kling 2.1](/docs/models/video/kling-2-1), [Kling 2.5 Turbo Pro](/docs/models/video/kling-2-5-turbo-pro), [Kling 2.6](/docs/models/video/kling-2-6), [Kling 3.0 Std](/docs/models/video/kling-3-0-std), [Kling 3.0 Turbo](/docs/models/video/kling-3-0-turbo) |
| Video | MiniMax | [Hailuo 2.3](/docs/models/video/hailuo-2-3), [Hailuo 2.3 Fast](/docs/models/video/hailuo-2-3-fast) |
| Video | Vidu | [Vidu Q3](/docs/models/video/vidu-q3) |
| Video | LTX | [LTX 2 19B](/docs/models/video/ltx-2-19b) |
| Video | Avatar and lip sync | [InfiniteTalk](/docs/models/video/infinitetalk) |
| Video | Video utilities | [Video Upscaler](/docs/models/video/video-upscaler), [Video Watermark Remover](/docs/models/video/video-watermark-remover) |
| Audio | Suno | [Suno](/docs/models/audio/suno) |
| Audio | Alibaba | [CosyVoice 3 Flash](/docs/models/audio/cosyvoice-3-flash), [CosyVoice 3 Plus](/docs/models/audio/cosyvoice-3-plus), [CosyVoice 3.5 Flash](/docs/models/audio/cosyvoice-3-5-flash), [CosyVoice 3.5 Plus](/docs/models/audio/cosyvoice-3-5-plus) |
| Audio | MiniMax | [MiniMax Speech 2.8](/docs/models/audio/minimax-speech-2-8), [MiniMax Voice](/docs/models/audio/minimax-voice) |
| Chat | Anthropic | [Claude](/docs/models/text/claude) |
| Chat | Google | [Gemini](/docs/models/text/gemini) |
| Chat | OpenAI | [GPT](/docs/models/text/openai-responses) |
| Utility | APIXO | [Prompt Optimizer](/docs/models/text/prompt-optimizer) |
## Choosing a generation model
| Goal | Good starting point |
| ------------------------------------ | ------------------------------------------------------------------------------- |
| Fast image prototype | Nano Banana |
| Higher-quality image generation | Flux 2, GPT Image 2, Seedream 4.0, Seedream 5.0, Seedream 5.0 Pro, Z-Image LoRA |
| Artistic image generation | Midjourney |
| Reference-guided image generation | Runway Gen4 Image, Runway Gen4 Image Turbo |
| Alibaba image generation and editing | Wan 2.7 Image |
| Image upscaling | Image Upscaler |
| Watermark cleanup | Image Watermark Remover |
| Text-to-video | Sora 2, Veo 3.1, Gemini Omni, Wan 2.5 |
| Image-to-video | Runway Gen4 Video Turbo, Sora 2 Pro, Hailuo 2.3, Kling 2.6 |
| Music generation | Suno |
| Text-to-speech or voice cloning | CosyVoice 3.5 Plus, MiniMax Speech 2.8, MiniMax Voice |
## From playground to API
If you came here from an APIXO model playground, open the matching model page in the sidebar. Each model page includes:
* Model ID and endpoints
* A copy-paste request
* Supported request parameters
* Response and result format
* Polling, webhook, error, and retry guidance
Pricing is maintained on the Pricing page. Use it as the source of truth for current model prices and route differences.