One AI API, flattened parameters. No hidden costs. Public AI API pricing for every model helps you budget with total precision.
to-imageCharged by USD/img, where "img" is the number of images, counted per image.to-videoCharged by USD/sec, where "sec" is the video duration, counted per second.to-audioCharged by USD/M chars, where "M chars" means one million input characters.Some models use different prices based on input parameters. For example, certain video generation models have higher prices for generating 1080p videos compared to 720p videos.
High-traffic models with public rates. Click through for parameter-level pricing.
[Core Function] Nano Banana 2 (Gemini 3.1 Flash Image) is an extremely fast text-to-image model. [Strengths] It is optimized for high-speed, high-volume visual generation, creative prompting, and rapid stylistic experimentation. [Best For] Highly recommended for: rapid creative iteration, generating large batches of images quickly, and artistic/stylized graphics. [Limitations] Do NOT use this model if you require strict, high-end photorealism; prefer Nano Banana Pro for higher-fidelity creative output. [Routing] Route to this model for 'fast', 'creative', or 'stylized' high-volume requests.
[Core Function] Seedance 2.0 T2V is ByteDance Dreamina Seedance 2.0 text-to-video. [Strengths] Supports 480p/720p/1080p/4k, 24 fps, 4-15s MP4 output. Text-only input — do not pass images, video, or audio. [Routing] Use for high-fidelity text-to-video when quality or 4k output is requested.
[Core Function] GPT Image 2 is a state-of-the-art text-to-image generation model. [Strengths] It excels at generating highly detailed, photorealistic images from text descriptions, with native support for ultra-high resolutions including 2K and 4K (up to 3840x2160). [Best For] Highly recommended for: cinematic landscapes, detailed character portraits, high-end commercial concept art, and any scenario requiring maximum resolution and visual fidelity. [Limitations] Do NOT use this model if you need a transparent background (e.g., for icons or UI assets), as it does not support the `background: transparent` parameter. [Routing] Use this model by default for all high-quality image generation requests. If the user explicitly asks for an image with a transparent background, route to GPT Image 1.5 instead.
[Core Function] Seedream 5.0 Lite is a smart, reasoning-enhanced image generation model with real-time web search capabilities. [Strengths] It excels at generating time-sensitive imagery, infographics, and content requiring deep world knowledge or online search, boasting superior prompt understanding and reasoning. [Best For] Highly recommended for: current-event posters, text-heavy designs, and concept art requiring complex logical reasoning. [Limitations] As a 'Lite' model, its absolute photorealistic aesthetic ceiling might be slightly lower than the specialized 4.5 model. [Routing] Use this model by default when the user needs real-time information, deep reasoning, or complex intent understanding in their image.
[Core Function] MAI Image 2.6 is Microsoft's latest text-to-image generation model in the MAI Image family. [Strengths] It improves text rendering, portraits, 3D imagery, and commercial photorealistic output compared with MAI Image 2.5. [Best For] Highly recommended for: marketing visuals, product hero shots, portraits, and prompts that need accurate on-image text. [Limitations] Do NOT use this if the requested width or height is below 768, or if width x height exceeds 1,048,576 pixels. Output is always PNG. auto_aspect_ratio and web_grounding are optional booleans; omit them unless the caller sets them. [Routing] Use this model when the latest MAI quality is required. For lower latency or cost, route to MAI Image 2.6 Flash.
[Core Function] MiniMax H3 T2V is a text-to-video generation model that creates video from a text prompt only. [Strengths] It supports 4-15 second clips, 768P or 2K output, and concrete aspect ratios from cinematic ultrawide to vertical. [Best For] Highly recommended for: prompt-only storyboards, character-driven shorts, cinematic B-roll from text, and high-resolution drafts without image inputs. [Limitations] Do NOT use this model if you need to condition on images, first or last frames, or reference videos. prompt, duration, resolution, and ratio are required; ratio must be one of the documented aspect ratios. [Routing] Choose MiniMax H3 T2V for text-only MiniMax H3 video. If the user provides a start or end frame, use MiniMax H3 FL2V. If they provide reference images, use MiniMax H3 I2V. If they provide reference videos, use MiniMax H3 V2V.
| Model | Type | Pricing | Max Generate ($10) |
|---|---|---|---|
| microsoft/mai-image-2.6-flash-edit | Image to Image | 454 Images | |
| microsoft/mai-image-2.6-edit | Image to Image | 212 Images | |
| microsoft/mai-image-2.6-flash | Text to Image | 512 Images | |
| microsoft/mai-image-2.6 | Text to Image | 257 Images | |
| bytedance/seedance-2.5-v2v | Video to Video | 32 Videos (5s ea.) | |
| bytedance/seedance-2.5-i2v | Image to Video | 19 Videos (5s ea.) | |
| bytedance/seedance-2.5-t2v | Text to Video | 19 Videos (5s ea.) | |
| bytedance/seedream-5.0-pro-multi-reference | Image to Image | 123 Images | |
| bytedance/seedream-5.0-pro-edit | Image to Image | 123 Images | |
| bytedance/seedream-5.0-pro | Text to Image | 123 Images | |
| bytedance/seedance-2.0-mini-v2v | Video to Video | 95 Videos (5s ea.) | |
| bytedance/seedance-2.0-mini-i2v | Image to Video | 50 Videos (5s ea.) | |
| bytedance/seedance-2.0-mini-t2v | Text to Video | 50 Videos (5s ea.) | |
| bytedance/seedance-2.0-fast-t2v | Text to Video | 33 Videos (5s ea.) | |
| bytedance/seedance-2.0-t2v | Text to Video | 28 Videos (5s ea.) | |
| bytedance/seedream-5.0-lite-edit | Image to Image | 285 Images | |
| bytedance/seedream-5.0-lite | Text to Image | 285 Images | |
| bytedance/seedance-2.0-fast-v2v | Video to Video | 60 Videos (5s ea.) | |
| bytedance/seedance-2.0-v2v | Video to Video | 46 Videos (5s ea.) | |
| bytedance/seedance-2.0-fast-i2v | Image to Video | 33 Videos (5s ea.) |
Use-case hubs with starting prices across the models in each collection.
It brings together the world's best video generation models, including text-to-video, image-to-video, and video editing capabilities.
Mainstream AI virtual try-on models—upload your model and clothing images to see how they fit.
This page aggregates high-quality AI digital human generation models, which can help you easily create digital human videos, such as lip-syncing.
This is a collection of the best models for style transfer, including image generation and video generation models.
A curated collection of lip-sync AI models.
The AI models here let you generate ready-to-use images or videos with just one click, covering applications such as marketing, advertising, short dramas, and more.
The best animation generation Models.
The best models for generating manga/anime images or videos.
AI models suitable for art design.
The best avatar-generating AI models.
The best portrait-generating AI models.
The mainstream image-colorization AI models.
The mainstream face-swap models.
The mainstream image upscalers.
The best LOGO generation design and creation AI models.
An AI models for restoring old photos.
The best voice-cloning models.
Family hubs that group variants (Lite / Fast / Standard) under one series page.
Nano Banana is an advanced AI image generation and editing model based on Google's Gemini technology, delivering fast, precise transformations with exceptional prompt understanding, consistent character editing, and high-quality visuals.
ByteDance's Seedance is a multimodal AI video generation model that creates cinematic 1080p multi-shot videos from text, images, audio, or video prompts with immersive audio-visual realism and director-level creative controls.
Google Veo 3.1 is the advanced successor to Veo 3, released in October 2025, enhancing 4K video generation with richer native audio, superior narrative control, precise image-to-video conversion, and seamless character consistency for dynamic storytelling.
ByteDance's Seedream is a high-fidelity text-to-image and editing model supporting native 4K resolution, batch generation, superior typography, and consistent character rendering for professional creative workflows.
The GPT-Image series by OpenAI consists of advanced multimodal models, such as GPT-Image-1 and GPT-Image-2, designed for generating and editing photorealistic images from text and image inputs.
CosyVoice is a family of open-source TTS models by FunAudioLLM that delivers high-quality speech synthesis, zero-shot voice cloning, and low-latency streaming from v1.0 to v3.0.
Fun is Alibaba's open-source, end-to-end automatic speech recognition toolkit supporting multilingual ASR, voice activity detection, punctuation restoration, and speaker diarization with real-time streaming capabilities.
Gemini Omni is Google's multimodal video generation and editing model that lets you create, remix, and edit videos as easily as having a conversation — blending text, images, and video input with natural language commands.
Grok Imagine is xAI's cross-modal AI model series that unifies text-to-image, image-to-image, text-to-video, image-to-video, and video-to-video generation in a single visual system, delivering studio-grade, photorealistic visuals with best-in-class text rendering and precise creative control.
Grok Voice is xAI's native speech-to-speech model powering expressive, real-time audio interactions with sub-second latency and agentic tool capabilities.
MiniMax's Hailuo 02 series is a top-ranked cinematic AI video suite for T2V/I2V, generating native 1080p clips with ultra-realistic physics, character consistency, and director-level controls.
MiniMax's Hailuo 2.3 series elevates cinematic AI video gen with 4K T2V/I2V, hyper-realistic physics/motion, extended clips, and advanced character consistency.
HappyHorse is a leading open-source AI video generation model with 15 billion parameters that jointly produces high-quality 1080p videos and synchronized audio from text or image prompts, currently topping the Artificial Analysis Video Arena leaderboard.
Google Imagen is Google's premier text-to-image diffusion model, excelling in photorealistic, high-resolution image generation from textual prompts with unmatched detail, creativity, and adherence to complex descriptions.
Kuaishou's Kling v3 series is an open multimodal AI suite for T2I/I2V/T2V, generating 4K cinematic visuals with native audio, multi-shot narratives, precise motion control, and consistent characters.
Microsoft's **MAI Image** series is a family of in-house, diffusion-based AI models, designed for state-of-the-art text-to-image generation and precise image-to-image editing, with a strong emphasis on photorealism, prompt adherence, and text rendering accuracy.
MiniMax Speech is a series of advanced text-to-speech (TTS) models that deliver ultra-low latency, highly natural and expressive speech synthesis, with support for zero-shot voice cloning and multilingual capabilities across variants like Turbo and HD.
PixVerse C1 is PixVerse's first AI video model purpose-built for film production, combining an industrial-grade action engine, cinematic VFX, storyboard-to-video conversion, and reference-guided character consistency to generate up to 15-second 1080p videos with native audio.
PixVerse V6 is PixVerse's flagship multi-shot AI video generation model that creates up to 15-second 1080p cinematic videos with native synchronized audio from text or image prompts, featuring improved camera control, consistent character emotion across scenes, and realistic physics simulation.
Qwen-Audio is a unified audio-language model series by Alibaba Cloud that processes speech, natural sounds, music, and singing across multiple languages and tasks, enabling universal audio understanding and multimodal interaction.
Qwen Image is Alibaba's unified 7B text-to-image generation and editing model series, renowned for high-fidelity visuals, superior text rendering, Photoshop-like layered editing, and top rankings on global leaderboards.
SkyReels is a powerful AI cinematic video generation model that transforms text and images into Hollywood-grade, human-centric videos with advanced facial animation, synchronized audio, and professional lighting — making it one of the leading open-source video foundation models available today.
Google Veo 3 is Google DeepMind's groundbreaking text-to-video AI model, unveiled at Google I/O 2025, that generates high-fidelity 4K cinematic videos with native synchronized audio from text or image prompts, offering professional controls and multi-scene coherence.
Vidu Q3 is Shengshu AI’s advanced text-to-video and image-to-video model that generates up to 16-second clips with native audio, enhanced motion, and precise camera control.
Alibaba's Wan (Wanx) series is a family of open-source multimodal foundation models developed by Alibaba Cloud that excels at high-quality text-to-video and text-to-image generation, featuring precise motion control, multilingual text rendering, and advanced instruction-following capabilities.
Compare starting prices across each vendor's catalog on Modellix.
Google is a leading provider of advanced AI media models, featuring Nano Banana and Imagen for high-fidelity image generation and editing, and Veo for scalable video synthesis.
ByteDance is a leading provider of advanced AI media models, featuring the Seedance series for high-fidelity multimodal video generation and the Seedream series for superior image creation and editing.
Alibaba Cloud is a leading provider of advanced AI models, featuring the Qwen series (including Qwen-Image for multimodal vision-language tasks) and the Wan series for high-fidelity video generation.
OpenAI is an AI research and deployment company founded in 2015, dedicated to developing safe and beneficial artificial general intelligence (AGI) that benefits all of humanity.
Kuaishou is a leading provider of advanced AI media models, featuring the Kling series (including Video and Image) for high-fidelity multimodal video and image generation.
MiniMax is a leading provider of advanced AI media models, featuring Hailuo for high-fidelity multimodal video generation and editing.
Starting prices by generation type — match billing unit to the capability you need.
Generate still images from text prompts. Billed per output image.
Edit, remix, and refine existing images. Billed per output image.
Generate video clips from text prompts. Billed per second of output.
Animate a source image or keyframe into motion. Billed per second of output.
Restyle, extend, or transform existing video. Billed per second.
Turn written text into natural speech and audio for voice workflows.
No. Modellix uses transparent usage-based pricing. You pay based on the public model price and your actual usage.
Model prices may change when provider costs or model availability changes. The latest price is always shown on the pricing page and model detail pages.
For high-volume or long-term usage, Modellix may offer account-level top-up or credit discounts. Model prices remain based on the public pricing table.
Yes. Go to the Console, open Billing > Orders, and click Invoice in the Actions column of the relevant order to download it yourself. For custom billing details or special requirements, contact support@modellix.ai.
Close the loop with blog/docs content that already ranks for model + pricing queries.
Generating, please do not close this page...
Join thousands of developers and creators. Start using the unified API for all models today.
