49
AI Models
13
Free
14
Image
10
Video
19
Text
4
Audio
2
Post-Prod
Model Developers
OpenAI
Creator of the GPT language model series and TTS voice synthesis
Anthropic
Creator of Claude language models, focused on safety & alignment
ByteDance
Creator of Seedream, Seedance & Dreamina visual AI models
Alibaba
Creator of Wan series and Qwen series AI models
Creator of the Gemini language model series
xAI
Creator of the Grok language model series
Black Forest Labs
Creator of the FLUX image editing model series
Kuaishou
Creator of the Kling video generation model
Mistral
Europe's leading open-source language model developer
Cheng et al.
Research team behind the MMAudio video-to-audio model (UIUC / Sony Research)
Free Image Models
Use top AI image models at zero cost. No credits needed.
Black Forest Labs
Free · High-quality T2I · Rate limited
Black Forest Labs
Free · Maximum quality · Rate limited
Black Forest Labs
Free · Flexible styles · Rate limited
Black Forest Labs
Free · Lightweight · Rate limited
ByteDance
Free · Bilingual · Rate limited · May queue
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| FLUX.2 Pro | Black Forest Labs | Free · High-quality T2I · Rate limited | $0 | Free |
| FLUX.2 Max | Black Forest Labs | Free · Maximum quality · Rate limited | $0 | Free |
| FLUX.2 Flex | Black Forest Labs | Free · Flexible styles · Rate limited | $0 | Free |
| FLUX.2 Klein 4B | Black Forest Labs | Free · Lightweight · Rate limited | $0 | Free |
| Seedream 4.5 | ByteDance | Free · Bilingual · Rate limited · May queue | $0 | Free |
Image Generation Models
Generate high-quality images from text descriptions with various styles and resolutions.
ByteDance
Latest flagship · Native bilingual · 4K ultra-HD
ByteDance
High-quality image generation · Bilingual
ByteDance
High-fidelity aesthetics · Artistic style
Alibaba
20B parameters · Excellent Chinese text rendering
Alibaba
Wan series image model · High resolution
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| Seedream 4.5 | ByteDance | Latest flagship · Native bilingual · 4K ultra-HD | $0.40 | Standard |
| Seedream 4 | ByteDance | High-quality image generation · Bilingual | $0.40 | Fast |
| Dreamina 3.1 | ByteDance | High-fidelity aesthetics · Artistic style | $0.60 | Premium |
| Qwen Image | Alibaba | 20B parameters · Excellent Chinese text rendering | $0.50 | Standard |
| Wan 2.6 Image | Alibaba | Wan series image model · High resolution | $0.80 | Fast |
Image Editing Models
Upload existing images for editing, enhancement, or style transformation.
Black Forest Labs
Context-aware editing · Best for image & text editing
Black Forest Labs
Multi-image context editing · Style consistency
ByteDance
Universal image editing · Image + text
Xintao Wang et al.
Image super-resolution · Quality enhancement
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| FLUX Kontext Pro | Black Forest Labs | Context-aware editing · Best for image & text editing | $0.80 | Premium |
| FLUX Kontext Pro Multi | Black Forest Labs | Multi-image context editing · Style consistency | $0.80 | Premium |
| UNO | ByteDance | Universal image editing · Image + text | $0.50 | Standard |
| Real-ESRGAN | Xintao Wang et al. | Image super-resolution · Quality enhancement | $0.50 | Fast |
Video Generation Models (Text-to-Video)
Auto-generate short videos from text descriptions. Some models support synchronized audio generation.
Alibaba
Ultra-fast generation · ~5s per video
Alibaba
High-definition resolution
Alibaba
Latest Wan series · Audio support
ByteDance
Cinematic quality · Audio support
Kuaishou
Best motion quality
ByteDance
Latest · Audio + lock camera · Up to 12s
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| Wan 2.2 — 480p Ultra Fast | Alibaba | Ultra-fast generation · ~5s per video | $0.10 | Fast |
| Wan 2.2 — 720p | Alibaba | High-definition resolution | $0.60 | Standard |
| Wan 2.6Audio | Alibaba | Latest Wan series · Audio support | $0.80 | Standard |
| Seedance 1.5 ProAudio | ByteDance | Cinematic quality · Audio support | $1.00 | Premium |
| Kling Video O3 | Kuaishou | Best motion quality | $1.20 | Premium |
| Seedance 2.0Audio | ByteDance | Latest · Audio + lock camera · Up to 12s | $1.20 | Premium |
Video Generation Models (Image-to-Video)
Transform static images into dynamic videos, bringing images to life.
Alibaba
Image-to-video · Fast
Alibaba
Image-to-video · HD
ByteDance
Image-to-video · Cinematic · Audio
ByteDance
Image-to-video · Audio + lock camera · 12s
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| Wan 2.2 i2v — 480p Fast | Alibaba | Image-to-video · Fast | $0.10 | Fast |
| Wan 2.2 i2v — 720p | Alibaba | Image-to-video · HD | $0.60 | Standard |
| Seedance 1.5 Pro i2vAudio | ByteDance | Image-to-video · Cinematic · Audio | $1.00 | Premium |
| Seedance 2.0 i2vAudio | ByteDance | Image-to-video · Audio + lock camera · 12s | $1.20 | Premium |
Free Text Models
Use top AI language models at zero cost. No credits needed.
OpenAI
Free · 120B open-source · Rate limited
NVIDIA
Free · 543B · Rate limited
Qwen
Free · 480B coding · Rate limited
Meta
Free · 70B · Rate limited
Free · 27B · Rate limited
Mistral
Free · 24B · Rate limited
DeepSeek
Free · Great for Chinese · Rate limited
Nous Research
Free · 405B · Rate limited
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| GPT-OSS 120B | OpenAI | Free · 120B open-source · Rate limited | $0 | Free |
| Nemotron 3 Super | NVIDIA | Free · 543B · Rate limited | $0 | Free |
| Qwen3 Coder 480B | Qwen | Free · 480B coding · Rate limited | $0 | Free |
| Llama 3.3 70B | Meta | Free · 70B · Rate limited | $0 | Free |
| Gemma 3 27B | Free · 27B · Rate limited | $0 | Free | |
| Mistral Small 3.1 24B | Mistral | Free · 24B · Rate limited | $0 | Free |
| DeepSeek V3 | DeepSeek | Free · Great for Chinese · Rate limited | $0 | Free |
| Hermes 3 405B | Nous Research | Free · 405B · Rate limited | $0 | Free |
Text Generation Models
Multiple leading AI language models for social content creation, rewriting, and optimization.
OpenAI
Flagship · Most capable overall
OpenAI
Lightweight · Cost-effective
OpenAI
Latest flagship model
Anthropic
Excellent writing quality
Anthropic
Fast · Cost-efficient
Ultra-fast · Low cost
High performance reasoning
xAI
Real-time aware
xAI
Lightweight and fast
Mistral
Efficient European model
Mistral
Balanced performance
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| GPT-4o | OpenAI | Flagship · Most capable overall | $12.50/1M in · $50/1M out | Premium |
| GPT-4o Mini | OpenAI | Lightweight · Cost-effective | $0.75/1M in · $3/1M out | Fast |
| GPT-5 | OpenAI | Latest flagship model | $6.25/1M in · $50/1M out | Premium |
| Claude Sonnet 4 | Anthropic | Excellent writing quality | $15/1M in · $75/1M out | Premium |
| Claude 3.5 Haiku | Anthropic | Fast · Cost-efficient | $4/1M in · $20/1M out | Fast |
| Gemini 2.5 Flash | Ultra-fast · Low cost | $1.50/1M in · $12.50/1M out | Fast | |
| Gemini 2.5 Pro | High performance reasoning | $6.25/1M in · $50/1M out | Premium | |
| Grok 3 | xAI | Real-time aware | $15/1M in · $75/1M out | Premium |
| Grok 3 Mini | xAI | Lightweight and fast | $1.50/1M in · $2.50/1M out | Fast |
| Mistral Small | Mistral | Efficient European model | $0.50/1M in · $1.50/1M out | Fast |
| Mistral Medium | Mistral | Balanced performance | $2/1M in · $10/1M out | Standard |
Voice Synthesis Models
Convert text to natural speech with multiple voice options and speed control.
OpenAI
High-quality TTS · 6 voices (alloy, echo, fable, onyx, nova, shimmer)
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| TTS-1 | OpenAI | High-quality TTS · 6 voices (alloy, echo, fable, onyx, nova, shimmer) | - | Standard |
Background Music Generation Models
Auto-generate synchronized background music from video content and text descriptions, no extra assets needed.
Cheng et al.
Video-to-audio · Multimodal sync · BGM generation
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| MMAudio V2 | Cheng et al. | Video-to-audio · Multimodal sync · BGM generation | - | Standard |
Video Narration Models
AI automatically analyzes video content and generates voiced narration. This feature uses two models in tandem: Gemini 2.5 Flash analyzes the video frames, then TTS-1 converts the generated script to speech.
Video analysis · Auto-generate narration
OpenAI
Narration synthesis · 6 voices
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| Gemini 2.5 FlashAnalysis | Video analysis · Auto-generate narration | - | Fast | |
| TTS-1Synthesis | OpenAI | Narration synthesis · 6 voices | - | Standard |
Post-Production Models
Video post-processing tools — object tracking, content replacement, and natural language editing.
Meta
Video object tracking · Click to track · Content replacement
Alibaba
Natural language video editing · AI smart modification
| Model | Developer | Description | Price | Tier |
|---|---|---|---|---|
| SAM2 Video | Meta | Video object tracking · Click to track · Content replacement | ~$0.04/run | Standard |
| Wan 2.7 VideoEdit | Alibaba | Natural language video editing · AI smart modification | ~$0.50/run | Premium |
Model Tier Guide
Zero cost with rate limits. May queue during peak hours.
Fastest generation, lowest cost. Ideal for quick iteration.
Best balance of speed and quality. Recommended for most uses.
Highest quality. Best for professional and important content.