Market

Explore and integrate cutting-edge AI models for image generation, video creation, and audio processing through unified APIs.

Welcome to the Market

Access a comprehensive collection of state-of-the-art AI models through our unified API platform. Choose from the latest image generation, video creation, and audio models to power your applications.

Image Models

Comprehensive collection of AI models for image generation, editing, and enhancement.

• Z-image — Fast text-to-image generation.

• Grok Imagine — Text-to-image, image-to-image and segment-based editing (Image 2.0)

• Flux-2 — Advanced text-to-image and image-to-image generation

• Google Imagen — State-of-the-art image generation (Imagen4 Fast/Ultra)

• Ideogram — Creative image generation with character consistency

• Qwen — Multilingual image generation and editing

• Recraft — Professional image upscaling and background removal

• Topaz — AI-powered image enhancement and upscaling

Video Models

Advanced AI models for video creation, editing, and transformation from text and images.

• Kling — High-quality video generation and AI avatars (v2.1, v2.5)

• Bytedance — Fast and efficient video generation (v1 Pro/Lite)

• Hailuo — High-quality video generation with multiple styles

• Wan — Advanced video generation with turbo performance

• Grok Imagine Video — Video generation from text and images

Audio Models

AI-powered audio processing including speech synthesis, recognition, and effects.

• ElevenLabs — High-quality text-to-speech, speech-to-text, and audio isolation

Chat Models

Advanced conversational AI models for natural language understanding and generation.

• Gemini 2.5 Pro — Advanced reasoning and long-context chat for complex prompts

Getting Started

Step 1 · Choose Your Model

Select the AI model that best fits your use case from the categories above.

Step 2 · Get API Key

Visit the API Key Management Page to obtain your API credentials.

Step 3 · Integrate

Follow the model-specific documentation to integrate the API into your application.

Step 4 · Start Creating

Begin generating content using your chosen AI model through simple API calls.

Authentication

All models in the market use the same authentication method:

Authorization: Bearer YOUR_API_KEY

Security Requirement

Keep your API Key strictly confidential. Never expose it in client-side code (browsers, mobile apps) or public repositories (like GitHub).

Unified API Structure

Most image, video and audio models use the unified task API below. Chat models and some model families (such as Suno) use their own endpoints; see each model page.

Create Task

POST https://ai.modelfold.online/v1/jobs/createTask

Query Task Status

GET https://ai.modelfold.online/v1/jobs/recordInfo?taskId={taskId}

Callback Notifications

Optional webhook callbacks notify you when a task succeeds or fails. See Webhook Verification.

TIP

Each model has unique parameters and capabilities. Refer to individual model documentation for detailed specifications.

Credits and Pricing

Different models consume different amounts of credits based on their computational requirements:

• Language Models: Charged per token usage

Check your remaining credits:

GET https://ai.modelfold.online/v1/chat/credit

Support

Need help choosing the right model or integrating our APIs?

• Email: support@modelfold.online
• Documentation: Browse model-specific guides in the navigation
• Community: Join our Discord server for discussions and updates