# AI Image Generator API

> Generate images from text prompts using 30+ AI models — Flux, Seedream, GPT-Image, HiDream, Qwen, Reve, Midjourney — through one MuApi.ai endpoint with credit-based pricing.

## Overview

MuApi gives you a single HTTP endpoint to call every leading text-to-image model in production. Submit a prompt, get back a request ID, poll for the result. No model-specific SDKs, no cold starts, no surprise billing — every model is priced per call in transparent credits, and you only pay for successful generations. Mix and match Flux Schnell for fast iteration, Seedream and HiDream for photoreal output, GPT-Image and Reve for text rendering, or Midjourney and Qwen for stylized art — all via the same `x-api-key` header and JSON body shape.

- 30+ text-to-image models exposed as `POST /api/v1/{model}` — Flux Dev/Schnell/Kontext, Seedream, GPT-Image, HiDream, Qwen, Reve, Midjourney, Wan
- Standard submit-then-poll workflow for every model — one client integration covers them all
- Auto-generated input forms in the playground; full Pydantic schema available via OpenAPI
- Credits charged on successful completion only — failures are free
- Optional webhook callback per request to skip polling

## API Pattern

Every model in this category uses the same submit-then-poll API:

```http
POST https://api.muapi.ai/api/v1/{model}
x-api-key: YOUR_API_KEY
Content-Type: application/json
```

Response: `{ "request_id": "abc123", "status": "processing" }`. Poll `GET https://api.muapi.ai/api/v1/predictions/{request_id}/result` until `status` is `completed` — the result URLs are in the `outputs[]` array. Optionally pass `?webhook=https://your-server` on the submit call to receive a callback instead of polling.

Get an API key at https://muapi.ai/access-keys.

## Quick Start

```bash
# 1. Submit
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/flux-schnell \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a serene mountain lake at dawn, photorealistic"}' | jq -r .request_id)

# 2. Poll
while :; do
  RESP=$(curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r .status)
  [ "$STATUS" = "completed" ] && echo "$RESP" | jq .outputs && break
  [ "$STATUS" = "failed" ] && echo "$RESP" && exit 1
  sleep 3
done
```

## Models in This Category

- [nano-banana](https://muapi.ai/playground/nano-banana): Nano Banana is an advanced AI model excelling in natural language-driven image generation and editing. It produces hyper-realistic, physics-aware visuals with…
  - Endpoint: `POST https://api.muapi.ai/api/v1/nano-banana`
  - Per-model llms.txt: https://muapi.ai/playground/nano-banana/llms.txt
  - Cost: 0.030 credits per call
- [nano-banana-pro](https://muapi.ai/playground/nano-banana-pro): Nano Banana 2 is the next-generation image generation developed by Google DeepMind, following the original Nano Banana (also known as Gemini 2.5 Flash Image).…
  - Endpoint: `POST https://api.muapi.ai/api/v1/nano-banana-pro`
  - Per-model llms.txt: https://muapi.ai/playground/nano-banana-pro/llms.txt
  - Cost: 0.120 credits per call
- [nano-banana-2](https://muapi.ai/playground/nano-banana-2): Nano Banana 2 (Gemini 3.1 Flash Image) is Google's most advanced image generation model, combining speed with high-fidelity 4K output and revolutionary charact…
  - Endpoint: `POST https://api.muapi.ai/api/v1/nano-banana-2`
  - Per-model llms.txt: https://muapi.ai/playground/nano-banana-2/llms.txt
  - Cost: 0.060 credits per call
- [flux-dev](https://muapi.ai/playground/flux-dev): Generate stunning visuals from simple text prompts. Flux Dev transforms your ideas into high-quality, creative images using powerful AI vision models. Perfect…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-dev`
  - Per-model llms.txt: https://muapi.ai/playground/flux-dev/llms.txt
  - Cost: 0.015 credits per call
- [bytedance-seedream-v3](https://muapi.ai/playground/bytedance-seedream-v3): Seedream is designed for generating visually rich and artistic images from text prompts. It excels at fantasy, anime, surrealism, and vibrant color composition…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seedream-v3`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seedream-v3/llms.txt
  - Cost: 0.030 credits per call
- [google-imagen4-ultra](https://muapi.ai/playground/google-imagen4-ultra): Imagen 4 Ultra is Google’s flagship model, designed for photorealism, rich textures, and production-level imagery. It produces crisp, high-resolution visuals w…
  - Endpoint: `POST https://api.muapi.ai/api/v1/google-imagen4-ultra`
  - Per-model llms.txt: https://muapi.ai/playground/google-imagen4-ultra/llms.txt
  - Cost: 0.060 credits per call
- [bytedance-seedream-v4.5](https://muapi.ai/playground/bytedance-seedream-v4.5): Seedream-v4.5 is ByteDance’s advanced text-to-image diffusion model designed for generating high-detail, high-contrast, cinematic and stylized images. It excel…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seedream-v4.5`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seedream-v4.5/llms.txt
  - Cost: 0.050 credits per call
- [flux-2-pro](https://muapi.ai/playground/flux-2-pro): Flux-2-Pro Text-to-Image is a premium, high-fidelity generative model capable of producing ultra-realistic, cinematic, and deeply detailed images from text pro…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-pro`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-pro/llms.txt
  - Cost: 0.032 credits per call
- [flux-schnell](https://muapi.ai/playground/flux-schnell): Flux Schnell is a lightning-fast image generation model designed for rapid iterations. It delivers good visual quality from text prompts almost instantly, maki…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-schnell`
  - Per-model llms.txt: https://muapi.ai/playground/flux-schnell/llms.txt
  - Cost: 0.003 credits per call
- [gpt-image-2-text-to-image](https://muapi.ai/playground/gpt-image-2-text-to-image): Generate high-quality images from text prompts using GPT Image 2, supporting up to 20,000 character prompts for detailed and precise image creation.
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-image-2-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-image-2-text-to-image/llms.txt
  - Cost: 0.090 credits per call
- [bytedance-seedream-v5.0](https://muapi.ai/playground/bytedance-seedream-v5.0): Seedream 5.0 Lite is ByteDance’s next-generation text-to-image model, delivering high-fidelity AI art with advanced visual reasoning and precise typography. Su…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seedream-v5.0`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seedream-v5.0/llms.txt
  - Cost: 0.033 credits per call
- [wan2.5-text-to-image](https://muapi.ai/playground/wan2.5-text-to-image): WAN 2.5 Text-to-Image generates high-quality, realistic or stylized images from textual descriptions. It supports detailed visual storytelling, cinematic compo…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.5-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.5-text-to-image/llms.txt
  - Cost: 0.040 credits per call
- [google-imagen4-fast](https://muapi.ai/playground/google-imagen4-fast): Imagen 4 Fast is optimized for speed and accessibility, allowing you to generate high-quality images in seconds. While slightly less detailed than the Ultra ve…
  - Endpoint: `POST https://api.muapi.ai/api/v1/google-imagen4-fast`
  - Per-model llms.txt: https://muapi.ai/playground/google-imagen4-fast/llms.txt
  - Cost: 0.020 credits per call
- [bytedance-seedream-v4](https://muapi.ai/playground/bytedance-seedream-v4): Seedream v4 generates stunning, high-fidelity images from text prompts. It’s designed for creativity with strong support for realism, fantasy, and artistic sty…
  - Endpoint: `POST https://api.muapi.ai/api/v1/bytedance-seedream-v4`
  - Per-model llms.txt: https://muapi.ai/playground/bytedance-seedream-v4/llms.txt
  - Cost: 0.040 credits per call
- [google-imagen4](https://muapi.ai/playground/google-imagen4): Google Imagen 4 is the latest text-to-image AI model from DeepMind, designed to produce stunningly photorealistic images with crisp detail, accurate text rende…
  - Endpoint: `POST https://api.muapi.ai/api/v1/google-imagen4`
  - Per-model llms.txt: https://muapi.ai/playground/google-imagen4/llms.txt
  - Cost: 0.030 credits per call
- [qwen-image](https://muapi.ai/playground/qwen-image): Generate high-quality, detailed images from text prompts in various styles — from realistic to artistic — perfect for creative visuals, product shots, and conc…
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image/llms.txt
  - Cost: 0.030 credits per call
- [gpt4o-text-to-image](https://muapi.ai/playground/gpt4o-text-to-image): Generate images from text prompts using GPT-4o's vision capabilities. Ideal for basic concept visuals, diagrams, and abstract compositions.
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt4o-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/gpt4o-text-to-image/llms.txt
  - Cost: 0.040 credits per call
- [hunyuan-image-3.0](https://muapi.ai/playground/hunyuan-image-3.0): Hunyuan Image 3.0 brings together powerful architecture (Mixture-of-Experts + autoregressive style) to produce richly detailed and coherent images from complex…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hunyuan-image-3.0`
  - Per-model llms.txt: https://muapi.ai/playground/hunyuan-image-3.0/llms.txt
  - Cost: 0.065 credits per call
- [flux-2-dev](https://muapi.ai/playground/flux-2-dev): Flux 2 Dev is a powerful text-to-image diffusion model designed for high-quality, fast, and highly detailed visual generation. It excels at creating cinematic…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-dev`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-dev/llms.txt
  - Cost: 0.015 credits per call
- [grok-imagine-text-to-image](https://muapi.ai/playground/grok-imagine-text-to-image): Grok Imagine is xAI’s high-quality image generation model that transforms text prompts into detailed, stylish, and visually expressive images. It excels at cre…
  - Endpoint: `POST https://api.muapi.ai/api/v1/grok-imagine-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/grok-imagine-text-to-image/llms.txt
  - Cost: 0.050 credits per call
- [flux-kontext-max-t2i](https://muapi.ai/playground/flux-kontext-max-t2i): Flux Kontext Max T2I delivers photorealistic or cinematic-quality images with exceptional detail. It's optimized for high-end visuals — from realistic humans t…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-kontext-max-t2i`
  - Per-model llms.txt: https://muapi.ai/playground/flux-kontext-max-t2i/llms.txt
  - Cost: 0.060 credits per call
- [flux-kontext-dev-t2i](https://muapi.ai/playground/flux-kontext-dev-t2i): Generates an image from a text prompt, with optional reference image for pose or style guidance. Ideal for controlled, consistent image creation using just a d…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-kontext-dev-t2i`
  - Per-model llms.txt: https://muapi.ai/playground/flux-kontext-dev-t2i/llms.txt
  - Cost: 0.020 credits per call
- [flux-kontext-pro-t2i](https://muapi.ai/playground/flux-kontext-pro-t2i): Flux Kontext Pro T2I offers fast and reliable generation with creative flexibility. It supports stylized prompts, character design, and fantasy themes while ma…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-kontext-pro-t2i`
  - Per-model llms.txt: https://muapi.ai/playground/flux-kontext-pro-t2i/llms.txt
  - Cost: 0.030 credits per call
- [wan2.1-text-to-image](https://muapi.ai/playground/wan2.1-text-to-image): WAN 2.1 is a powerful AI model that transforms text prompts into high-resolution, photorealistic images. It excels at detailed object rendering, realistic ligh…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.1-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.1-text-to-image/llms.txt
  - Cost: 0.030 credits per call
- [wan2.6-text-to-image](https://muapi.ai/playground/wan2.6-text-to-image): WAN 2.6 Text-to-Image generates detailed, cinematic still images from text prompts. It focuses on strong composition, atmospheric lighting, and clear subject s…
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.6-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.6-text-to-image/llms.txt
  - Cost: 0.040 credits per call
- [ideogram-v3-t2i](https://muapi.ai/playground/ideogram-v3-t2i): Ideogram v3 is an advanced text-to-image model designed for creating highly detailed and visually striking images directly from text prompts. It’s especially g…
  - Endpoint: `POST https://api.muapi.ai/api/v1/ideogram-v3-t2i`
  - Per-model llms.txt: https://muapi.ai/playground/ideogram-v3-t2i/llms.txt
  - Cost: 0.020 credits per call
- [z-image-turbo](https://muapi.ai/playground/z-image-turbo): Z-Image Turbo is a high-speed text-to-image model optimized for fast creative generation. It produces detailed, high-contrast, high-resolution images with stro…
  - Endpoint: `POST https://api.muapi.ai/api/v1/z-image-turbo`
  - Per-model llms.txt: https://muapi.ai/playground/z-image-turbo/llms.txt
  - Cost: 0.007 credits per call
- [ai-anime-generator](https://muapi.ai/playground/ai-anime-generator): Create stunning anime-style artwork instantly with our AI Anime Generator. Customize characters, scenes, and styles effortlessly in seconds!
  - Endpoint: `POST https://api.muapi.ai/api/v1/ai-anime-generator`
  - Per-model llms.txt: https://muapi.ai/playground/ai-anime-generator/llms.txt
  - Cost: 0.030 credits per call
- [wan2.7-text-to-image-pro](https://muapi.ai/playground/wan2.7-text-to-image-pro): Alibaba WAN 2.7 Text-to-Image Pro generates high-quality images up to 4K from text prompts with thinking mode for enhanced image quality.
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.7-text-to-image-pro`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.7-text-to-image-pro/llms.txt
  - Cost: 0.100 credits per call
- [chroma-image](https://muapi.ai/playground/chroma-image): Croma Image is an advanced text-to-image generation model designed for high-quality, creative, and versatile visuals. It can produce anything from photorealist…
  - Endpoint: `POST https://api.muapi.ai/api/v1/chroma-image`
  - Per-model llms.txt: https://muapi.ai/playground/chroma-image/llms.txt
  - Cost: 0.020 credits per call
- [midjourney-v8](https://muapi.ai/playground/midjourney-v8): Generate 4 photorealistic images per run with Midjourney V8. Improved coherence and detail over V7. Supports text-to-image and reference image guidance.
  - Endpoint: `POST https://api.muapi.ai/api/v1/midjourney-v8`
  - Per-model llms.txt: https://muapi.ai/playground/midjourney-v8/llms.txt
  - Cost: 0.100 credits per call
- [flux-2-klein-9b-turbo](https://muapi.ai/playground/flux-2-klein-9b-turbo): Flux-2-Klein-9B Turbo is a high-performance, mid-size text-to-image model. This distilled variant of Klein 9B provides a superior balance of speed and detail,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-9b-turbo`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-9b-turbo/llms.txt
  - Cost: 0.006 credits per call
- [gpt-image-1.5](https://muapi.ai/playground/gpt-image-1.5): GPT-Image-1.5 is a high-quality text-to-image generation model designed for rich visual reasoning, detailed compositions, and strong prompt understanding. It e…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-image-1.5`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-image-1.5/llms.txt
  - Cost: 0.054 credits per call
- [hidream-i1-dev](https://muapi.ai/playground/hidream-i1-dev): Optimized for speed, this variant generates images in just a few steps. Ideal for previews, real-time applications, and use cases where fast results are more i…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hidream-i1-dev`
  - Per-model llms.txt: https://muapi.ai/playground/hidream-i1-dev/llms.txt
  - Cost: 0.020 credits per call
- [z-image-base](https://muapi.ai/playground/z-image-base): Z-Image Base is a general-purpose text-to-image model designed for reliable, high-quality image generation from natural language prompts. It focuses on clear c…
  - Endpoint: `POST https://api.muapi.ai/api/v1/z-image-base`
  - Per-model llms.txt: https://muapi.ai/playground/z-image-base/llms.txt
  - Cost: 0.013 credits per call
- [kling-o1-text-to-image](https://muapi.ai/playground/kling-o1-text-to-image): Kling O1 Text-to-Image is a high-fidelity creative image model that converts rich natural-language prompts into ultra-detailed stills. It excels at cinematic c…
  - Endpoint: `POST https://api.muapi.ai/api/v1/kling-o1-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/kling-o1-text-to-image/llms.txt
  - Cost: 0.036 credits per call
- [flux-krea-dev](https://muapi.ai/playground/flux-krea-dev): Flux Krea Dev is a text-to-image model built by Black Forest Labs in collaboration with Krea AI, designed to generate highly photorealistic images that avoid t…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-krea-dev`
  - Per-model llms.txt: https://muapi.ai/playground/flux-krea-dev/llms.txt
  - Cost: 0.015 credits per call
- [wan2.7-text-to-image](https://muapi.ai/playground/wan2.7-text-to-image): Alibaba WAN 2.7 Text-to-Image generates high-quality images from text prompts with thinking mode for enhanced image quality.
  - Endpoint: `POST https://api.muapi.ai/api/v1/wan2.7-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/wan2.7-text-to-image/llms.txt
  - Cost: 0.050 credits per call
- [qwen-image-2.0-pro](https://muapi.ai/playground/qwen-image-2.0-pro): Qwen 2.0 Pro Text to Image model with maximum realism and fidelity.
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-2.0-pro`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-2.0-pro/llms.txt
  - Cost: 0.090 credits per call
- [midjourney-v7](https://muapi.ai/playground/midjourney-v7): Generate 4 photorealistic images per run with Midjourney V7. Supports text-to-image and reference image guidance via source_image_url.
  - Endpoint: `POST https://api.muapi.ai/api/v1/midjourney-v7`
  - Per-model llms.txt: https://muapi.ai/playground/midjourney-v7/llms.txt
  - Cost: 0.100 credits per call
- [perfect-pony-xl](https://muapi.ai/playground/perfect-pony-xl): Pony XL is a high-quality image generation model based on Stable Diffusion XL architecture. It specializes in character art, hybrid styles, and producing detai…
  - Endpoint: `POST https://api.muapi.ai/api/v1/perfect-pony-xl`
  - Per-model llms.txt: https://muapi.ai/playground/perfect-pony-xl/llms.txt
  - Cost: 0.020 credits per call
- [sdxl-image](https://muapi.ai/playground/sdxl-image): SDXL is a high-quality, large Stable Diffusion model for creating photorealistic and stylized images from text. It excels at fine detail, realistic lighting, a…
  - Endpoint: `POST https://api.muapi.ai/api/v1/sdxl-image`
  - Per-model llms.txt: https://muapi.ai/playground/sdxl-image/llms.txt
  - Cost: 0.004 credits per call
- [hidream-i1-full](https://muapi.ai/playground/hidream-i1-full): The most advanced version of HiDream I1, delivering high-resolution, detailed images with superior prompt understanding. Best suited for production, content cr…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hidream-i1-full`
  - Per-model llms.txt: https://muapi.ai/playground/hidream-i1-full/llms.txt
  - Cost: 0.040 credits per call
- [hunyuan-image-2.1](https://muapi.ai/playground/hunyuan-image-2.1): Hunyuan Image is a powerful text-to-image generation model that produces photorealistic and highly detailed visuals. It excels at creating portraits, environme…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hunyuan-image-2.1`
  - Per-model llms.txt: https://muapi.ai/playground/hunyuan-image-2.1/llms.txt
  - Cost: 0.035 credits per call
- [midjourney-niji](https://muapi.ai/playground/midjourney-niji): Generate 4 anime and illustration-style images per run with Midjourney Niji. Optimized for character art, manga, and stylized illustrations. Supports reference…
  - Endpoint: `POST https://api.muapi.ai/api/v1/midjourney-niji`
  - Per-model llms.txt: https://muapi.ai/playground/midjourney-niji/llms.txt
  - Cost: 0.100 credits per call
- [flux-2-klein-9b](https://muapi.ai/playground/flux-2-klein-9b): Flux-2-Klein-9B is a mid-size text-to-image model that balances detail quality and generation speed. It handles richer lighting, better textures, and more nuan…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-9b`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-9b/llms.txt
  - Cost: 0.013 credits per call
- [z-image-p](https://muapi.ai/playground/z-image-p): Z-Image P is based on PiAPI's Qubico/z-image text-to-image model.
  - Endpoint: `POST https://api.muapi.ai/api/v1/z-image-p`
  - Per-model llms.txt: https://muapi.ai/playground/z-image-p/llms.txt
  - Cost: 0.004 credits per call
- [leonardoai-phoenix-1.0](https://muapi.ai/playground/leonardoai-phoenix-1.0): LeonardoAI Phoenix 1.0 is a professional-grade AI image model designed for realistic, cinematic, and highly detailed visuals. It excels at interpreting complex…
  - Endpoint: `POST https://api.muapi.ai/api/v1/leonardoai-phoenix-1.0`
  - Per-model llms.txt: https://muapi.ai/playground/leonardoai-phoenix-1.0/llms.txt
  - Cost: 0.050 credits per call
- [neta-lumina](https://muapi.ai/playground/neta-lumina): Neta Lumina is a powerful anime-style text-to-image model developed by Neta.art Lab. It’s built on Lumina-Image-2.0, fine-tuned with over 13 million high-quali…
  - Endpoint: `POST https://api.muapi.ai/api/v1/neta-lumina`
  - Per-model llms.txt: https://muapi.ai/playground/neta-lumina/llms.txt
  - Cost: 0.020 credits per call
- [leonardoai-lucid-origin](https://muapi.ai/playground/leonardoai-lucid-origin): Lucid Origin is LeonardoAI’s advanced image generation model, designed for ultra-realistic, vibrant, and highly detailed visuals. It excels at creating photore…
  - Endpoint: `POST https://api.muapi.ai/api/v1/leonardoai-lucid-origin`
  - Per-model llms.txt: https://muapi.ai/playground/leonardoai-lucid-origin/llms.txt
  - Cost: 0.030 credits per call
- [flux-2-klein-4b](https://muapi.ai/playground/flux-2-klein-4b): Flux-2-Klein-4B is a lightweight, fast text-to-image model optimized for clear subject rendering, good prompt adherence, and efficient generation. It works bes…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-4b`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-4b/llms.txt
  - Cost: 0.010 credits per call
- [reve-text-to-image](https://muapi.ai/playground/reve-text-to-image): Generate images from text prompts using reve's vision capabilities. Ideal for basic concept visuals, diagrams, and abstract compositions.
  - Endpoint: `POST https://api.muapi.ai/api/v1/reve-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/reve-text-to-image/llms.txt
  - Cost: 0.032 credits per call
- [flux-2-flex](https://muapi.ai/playground/flux-2-flex): Flux-2-Flex Text-to-Image is a flexible, high-fidelity generative model capable of producing detailed, imaginative, and stylistically rich scenes from text alo…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-flex`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-flex/llms.txt
  - Cost: 0.090 credits per call
- [flux-2-klein-4b-turbo](https://muapi.ai/playground/flux-2-klein-4b-turbo): Flux-2-Klein-4B Turbo is an ultra-fast, high-efficiency text-to-image model. It is a distilled version of the Klein 4B model, designed for near-instant renderi…
  - Endpoint: `POST https://api.muapi.ai/api/v1/flux-2-klein-4b-turbo`
  - Per-model llms.txt: https://muapi.ai/playground/flux-2-klein-4b-turbo/llms.txt
  - Cost: 0.005 credits per call
- [hidream-i1-fast](https://muapi.ai/playground/hidream-i1-fast): Optimized for speed, this variant generates images in just a few steps. Ideal for previews, real-time applications, and use cases where fast results are more i…
  - Endpoint: `POST https://api.muapi.ai/api/v1/hidream-i1-fast`
  - Per-model llms.txt: https://muapi.ai/playground/hidream-i1-fast/llms.txt
  - Cost: 0.008 credits per call
- [qwen-image-2.0](https://muapi.ai/playground/qwen-image-2.0): Qwen 2.0 Text to Image model with enhanced realism.
  - Endpoint: `POST https://api.muapi.ai/api/v1/qwen-image-2.0`
  - Per-model llms.txt: https://muapi.ai/playground/qwen-image-2.0/llms.txt
  - Cost: 0.040 credits per call
- [vidu-q2-text-to-image](https://muapi.ai/playground/vidu-q2-text-to-image): VIDU Text-to-Image Q2 is a high-quality generative model focused on producing vivid, dynamic, and cinematic still images using natural language prompts. It exc…
  - Endpoint: `POST https://api.muapi.ai/api/v1/vidu-q2-text-to-image`
  - Per-model llms.txt: https://muapi.ai/playground/vidu-q2-text-to-image/llms.txt
  - Cost: 0.040 credits per call
- [tiktok-carousel](https://muapi.ai/playground/tiktok-carousel): AI TikTok Carousel Generator — create viral TikTok carousel posts from a single text prompt. Choose a proven storytelling format (Problem-Solution, Listicle, T…
  - Endpoint: `POST https://api.muapi.ai/api/v1/tiktok-carousel`
  - Per-model llms.txt: https://muapi.ai/playground/tiktok-carousel/llms.txt
  - Cost: 0.028 credits per call
- [grok-imagine-text-to-image-quality](https://muapi.ai/playground/grok-imagine-text-to-image-quality): Grok Imagine Quality is xAI's high-fidelity text-to-image mode that prioritizes accuracy and detail over speed. It produces sharper, more visually accurate ima…
  - Endpoint: `POST https://api.muapi.ai/api/v1/grok-imagine-text-to-image-quality`
  - Per-model llms.txt: https://muapi.ai/playground/grok-imagine-text-to-image-quality/llms.txt
  - Cost: 0.100 credits per call

## FAQ

**Which AI image generator API is the best?**

It depends on the trade-off you want. Flux Schnell and Seedream lead on photoreal speed; HiDream and Reve produce the most accurate in-image text; Midjourney and Qwen Image lead on stylized artistic output; GPT-Image is the strongest generalist with editing support. MuApi exposes all of them so you can A/B in code without rewriting your client.

**How do I authenticate?**

Send your MuApi key as the `x-api-key` header on every request. Create one at https://muapi.ai/access-keys.

**What does a request look like?**

POST a JSON body to `https://api.muapi.ai/api/v1/{model}` (e.g. `flux-schnell`). You get back a `request_id`. Poll `GET /api/v1/predictions/{request_id}/result` until `status` is `completed`, then read the image URLs from `outputs[]`.

**Is there a free tier?**

Yes — new accounts get free credits to try every model in the playground before committing.

**How is pricing calculated?**

Each model has a per-call cost in credits, listed on the playground page. Some models (e.g. variable-resolution or duration-based ones) compute cost dynamically from the request payload — the playground shows the live calculation as you tweak inputs.

**Can I use this from an agent or LLM?**

Yes. MuApi ships an MCP server (`muapi mcp serve`) that exposes every model as a tool — drop it into Claude Code, Cursor, or any MCP-aware agent and call image generation by name.

## Agent Integration

MuApi ships an MCP server so agents (Claude Code, Cursor, custom) can call every model in this category as a tool:

```bash
npm install -g muapi-cli
muapi auth login
muapi mcp serve  # exposes all MuApi models as MCP tools
```

## Resources

- Category page: https://muapi.ai/playground/group/text-to-image
- Global llms.txt: https://muapi.ai/llms.txt
- API docs: https://muapi.ai/docs
- OpenAPI spec: https://api.muapi.ai/openapi.json