Loading...
動画、画像、音声、3D、LLMの生成モデルを比較
37 個のモデルが利用可能
| モデル | カテゴリ | プロバイダ | コスト | 対応パラメータ | |
|---|---|---|---|---|---|
ace-step Lightweight music generation for quick prototyping and background music | audio | music_generation_v3_5 | 2クレジット | promptduration | 試す |
claude Anthropic Claude with powerful reasoning and long-context understanding | llm | claude-sonnet-4-6 | 2クレジット | texttemperaturemax_tokens | 試す |
claude-code Claude Code optimized for software development and engineering tasks | llm | claude-sonnet-4-6 | 2クレジット | texttemperaturemax_tokens | 試す |
deep-research Autonomous research agent capable of executing multi-step investigative research | llm | deepseek-reasoner | 5クレジット | texttemperaturemax_tokens | 試す |
deepseek Powerful reasoning model with exceptional math and coding capabilities | llm | deepseek-chat | 1クレジット | texttemperaturemax_tokens | 試す |
flux-api High-quality text-to-image generation with exceptional detail | image | flux-2-flex | 4クレジット | promptnegative_promptaspect_ratioseedcountquality | 試す |
flux-kontext Flux with contextual understanding for more coherent outputs | image | flux-kontext-pro | 5クレジット | promptimage_urlaspect_ratioseedcountquality | 試す |
gpt-4o OpenAI's most capable multimodal model | llm | gpt-4o | 2クレジット | texttemperaturemax_tokens | 試す |
gpt-image-1 OpenAI's GPT-powered image generation | image | gpt-image-1-official | 6クレジット | promptaspect_ratioseedcountquality | 試す |
gpt-image-1-5 GPT Image 1 upgraded version with further improved generation quality | image | gpt-image-1.5-official | 6クレジット | promptaspect_ratioseedcountquality | 試す |
gpt-image-2-0 OpenAI's latest GPT Image 2.0 generation with higher resolution support | image | gpt-image-2 | 7クレジット | promptsizeresolutioncountimage_urls | 試す |
hailuo-api Fast and efficient video generation optimized for creators and marketers | video | MiniMax-Hailuo-2.3 | 10クレジット | promptnegative_promptaspect_ratiodurationseedquality | 試す |
imagen-4 Imagen 4 text-to-image generation through APIMart | image | imagen-4.0-apimart | 5クレジット | promptsizecount | 試す |
kling-2-5 Balanced performance and quality for professional video creation | video | kling-o3-text-to-video | 11クレジット | promptnegative_promptaspect_ratiodurationseedquality | 試す |
kling-2-6 Enhanced Kling 2.x with improved detail and motion smoothness | video | kling-v2-6 | 13クレジット | promptimage_urlsnegative_promptaspect_ratiodurationquality | 試す |
kling-3 High-quality cinematic video generation with realistic motion and physics | video | kling-v3-text-to-video | 15クレジット | promptimage_urlnegative_promptaspect_ratiodurationseedquality | 試す |
kling-3-omni Omni-modal Kling 3.0 supporting multiple input types for video generation | video | kling-v3-omni | 18クレジット | promptimage_urlnegative_promptaspect_ratiodurationseedquality | 試す |
kling-ai-avatar Generate personalized AI avatar videos with consistent character identity | video | kling-o3-reference-to-video | 14クレジット | promptimage_urlvideo_urlaspect_ratioduration | 試す |
kling-api Kuaishou's flagship video generation API with high-quality output | video | kling-v3-text-to-video | 12クレジット | promptimage_urlnegative_promptaspect_ratiodurationseedquality | 試す |
kling-o1 Optimized Kling model with faster inference and improved consistency | video | kling-video-o1 | 10クレジット | promptimage_urlnegative_promptaspect_ratiodurationseedquality | 試す |
nano-banana Fast and affordable image generation | image | nano-banana-2-lite | 2クレジット | promptaspect_ratioseedquality | 試す |
nano-banana-2 Second-generation Nano Banana with stronger semantic understanding | image | gemini-3.1-flash-image-preview | 2クレジット | promptaspect_ratioseedquality | 試す |
nano-banana-pro Nano Banana Pro with significantly improved quality and detail | image | gemini-3-pro-image-preview | 3クレジット | promptaspect_ratioseedquality | 試す |
pixverse-v6 Pixverse v6 unified video generation for fast text and image driven clips | video | pixverse-v6 | 12クレジット | promptimage_urlsnegative_promptaspect_ratiodurationseedquality | 試す |
seedance-1-0-pro Professional image-to-video with fluid motion and high fidelity | video | seedance-1.5-pro | 14クレジット | promptimage_urlaspect_ratiodurationseedquality | 試す |
seedance-2-0 Next-gen image-to-video with upgraded motion dynamics and detail | video | seedance-2.0-text-to-video | 16クレジット | promptimage_urlaspect_ratiodurationseedquality | 試す |
seedream-4-0 Seedream 4.0 with balanced quality and cost for most scenarios | image | doubao-seedream-4.0 | 4クレジット | promptaspect_ratioseedcountquality | 試す |
seedream-4-5 Seedream 4.5 with higher fidelity image generation and editing | image | doubao-seedream-4.5 | 5クレジット | promptimage_urlssizequalitycount | 試す |
seedream-5-0 ByteDance Seedream 5.0 with commercial-grade image quality | image | doubao-seedream-5.0-lite | 5クレジット | promptaspect_ratioseedcountquality | 試す |
skyreels-api Cinematic video generation with advanced camera movement and scene composition | video | skyreels-v4-std | 13クレジット | promptnegative_promptaspect_ratiodurationseedquality | 試す |
sora-2 Sora 2 text and image to video generation via APIMart | video | sora-2 | 20クレジット | promptimage_urlsaspect_ratiodurationquality | 試す |
veo-3-1 Refined Veo with improved temporal consistency and longer videos | video | veo-3.1-generate-preview | 22クレジット | promptimage_urlsgeneration_typenegative_promptaspect_ratiodurationqualityseed | 試す |
vidu-q3 Vidu Q3 Pro video generation with strong reference adherence | video | viduq3-pro | 14クレジット | promptimage_urlsaspect_ratiodurationseedquality | 試す |
wan-2-6 Latest generation Wan with state-of-the-art video synthesis capabilities | video | wan2.6-text-to-video | 12クレジット | promptnegative_promptaspect_ratiodurationseedquality | 試す |
wan-2-7 Wan 2.7 video generation with upgraded motion and higher fidelity | video | wan2.7 | 14クレジット | promptimage_urlsnegative_promptaspect_ratiodurationseedquality | 試す |
wan-2-7-image Wan 2.7 image generation and editing with reference image support | image | wan2.7-image-pro | 4クレジット | promptimage_urlssizeresolutionnegative_promptseedcount | 試す |
z-image-turbo Ultra-fast Z Image Turbo generation | image | z-image-turbo | 2クレジット | promptaspect_ratioseedquality | 試す |
music_generation_v3_5
Lightweight music generation for quick prototyping and background music
対応パラメータ
claude-sonnet-4-6
Anthropic Claude with powerful reasoning and long-context understanding
対応パラメータ
claude-sonnet-4-6
Claude Code optimized for software development and engineering tasks
対応パラメータ
deepseek-reasoner
Autonomous research agent capable of executing multi-step investigative research
対応パラメータ
deepseek-chat
Powerful reasoning model with exceptional math and coding capabilities
対応パラメータ
flux-2-flex
High-quality text-to-image generation with exceptional detail
対応パラメータ
flux-kontext-pro
Flux with contextual understanding for more coherent outputs
対応パラメータ
gpt-image-1-official
OpenAI's GPT-powered image generation
対応パラメータ
gpt-image-1.5-official
GPT Image 1 upgraded version with further improved generation quality
対応パラメータ
gpt-image-2
OpenAI's latest GPT Image 2.0 generation with higher resolution support
対応パラメータ
MiniMax-Hailuo-2.3
Fast and efficient video generation optimized for creators and marketers
対応パラメータ
imagen-4.0-apimart
Imagen 4 text-to-image generation through APIMart
対応パラメータ
kling-o3-text-to-video
Balanced performance and quality for professional video creation
対応パラメータ
kling-v2-6
Enhanced Kling 2.x with improved detail and motion smoothness
対応パラメータ
kling-v3-text-to-video
High-quality cinematic video generation with realistic motion and physics
対応パラメータ
kling-v3-omni
Omni-modal Kling 3.0 supporting multiple input types for video generation
対応パラメータ
kling-o3-reference-to-video
Generate personalized AI avatar videos with consistent character identity
対応パラメータ
kling-v3-text-to-video
Kuaishou's flagship video generation API with high-quality output
対応パラメータ
kling-video-o1
Optimized Kling model with faster inference and improved consistency
対応パラメータ
nano-banana-2-lite
Fast and affordable image generation
対応パラメータ
gemini-3.1-flash-image-preview
Second-generation Nano Banana with stronger semantic understanding
対応パラメータ
gemini-3-pro-image-preview
Nano Banana Pro with significantly improved quality and detail
対応パラメータ
pixverse-v6
Pixverse v6 unified video generation for fast text and image driven clips
対応パラメータ
seedance-1.5-pro
Professional image-to-video with fluid motion and high fidelity
対応パラメータ
seedance-2.0-text-to-video
Next-gen image-to-video with upgraded motion dynamics and detail
対応パラメータ
doubao-seedream-4.0
Seedream 4.0 with balanced quality and cost for most scenarios
対応パラメータ
doubao-seedream-4.5
Seedream 4.5 with higher fidelity image generation and editing
対応パラメータ
doubao-seedream-5.0-lite
ByteDance Seedream 5.0 with commercial-grade image quality
対応パラメータ
skyreels-v4-std
Cinematic video generation with advanced camera movement and scene composition
対応パラメータ
sora-2
Sora 2 text and image to video generation via APIMart
対応パラメータ
veo-3.1-generate-preview
Refined Veo with improved temporal consistency and longer videos
対応パラメータ
viduq3-pro
Vidu Q3 Pro video generation with strong reference adherence
対応パラメータ
wan2.6-text-to-video
Latest generation Wan with state-of-the-art video synthesis capabilities
対応パラメータ
wan2.7
Wan 2.7 video generation with upgraded motion and higher fidelity
対応パラメータ
wan2.7-image-pro
Wan 2.7 image generation and editing with reference image support
対応パラメータ
z-image-turbo
Ultra-fast Z Image Turbo generation
対応パラメータ