Moonshot AI

Kimi K3.1 Pro

Moonshot AI's flagship text model, focused on document understanding and long-context text generation, suitable for research and agent tasks

From $0.216 /1M tokens

Kandinsky 6.0 Pro

An open-source diffusion video model that generates about 5 seconds at a time with 44 kHz synchronized audio and lip-sync, supports text-to-video and image-to-video, and can upscale to Full-HD

From $1.93 /video

Black Forest Labs

FLUX.1 Kontext Max

The flagship image editing version of the Kontext series, skilled at making local edits according to natural language instructions, with stronger prompt adherence and in-image text layout, suitable for brand visuals and batch storyboard production

From $0.071 /image

Alibaba

Qwen Audio 3.0 TTS

Alibaba Tongyi's managed multilingual speech synthesis series, with two tiers—low-latency Flash and high-quality Plus—supporting natural language instructions to control emotion and expressive style

From $0.030 /1,000 characters

Vidu

Vidu Q3

A reference image-to-video model for advertising and short social videos that constrains subject appearance and composition, suitable for rapid production and multi-version iteration

From $0.149 /second

Kuaishou

Kling 4.0

Kuaishou video generation model that can generate 30-second videos with stereo audio in a single pass, supports multi-keyframe and first/last frame control, and is suitable for marketing short films and storyboard previews

From $0.330 /second

OpenAI

GPT Image 2.5

OpenAI's two-tier image generation and editing models: Flare focuses on speed, Sunburst pursues precision, covering both text-to-image and multi-turn image refinement

From $0.017 /image

Alibaba

Wan 3.0 Video

Alibaba's new-generation video generation model in the Wan series, capable of producing roughly 30-second 1080p clips in a single pass, supporting reference materials to maintain subject consistency, and the first to support structured document-type inputs

From $0.040 /second

xAI

Grok Imagine 1.5

xAI's video generation model; image-to-video can animate still images and generate synchronized audio, supporting 480p to 1080p and clips up to 15 seconds long

From $0.011 /second

ByteDance

Seedance 2.5

ByteDance Seed's joint audio-video generation model, supporting continuous clips up to 30 seconds and up to 4K, with precise visual control via multimodal references and timestamp-level editing

From $0.121 /second

ByteDance

Seedance 2.0

ByteDance's multimodal video generation model, supporting text-to-video, image-to-video, and reference-based video generation, and capable of producing multi-shot, cinematic short films with native synchronized audio

From $0.017 /second

Google

Nano Banana Pro

A quality-first image generation and editing model built on the Gemini 3 Pro reasoning backbone, stronger at multi-image character consistency and text rendering, supporting native 2K output with intelligent upscaling to 4K

From $0.057 /image

Google

Nano Banana 2

Google's fast image model for scaled-up image generation, supporting 512px up to native 4K and multiple aspect ratios, generating with real-time information from Search, suitable for high-frequency creation

From $0.036 /image

Google

Nano Banana

Designed for natural-language-driven image generation and multi-turn conversational retouching, it preserves character and subject consistency well during edits and covers generation, editing, and enhancement

From $0.021 /image

OpenAI

GPT Image 2

OpenAI's image generation and editing model, focused on photorealistic quality, high-precision text rendering, and native 4K output, suited for commercial materials and product images that contain text

From $0.007 /image

Zhipu AI

GLM 5.3

Zhipu's flagship text reasoning model, focused on complex software engineering and long-horizon Agent tasks, with roughly 1M context, always-on reasoning and support for multiple reasoning-effort levels, delivering more token-efficient output at the same score

From $0.855 /1M tokens

OpenAI

GPT 6

OpenAI's GPT-6 family of text models, layered by task difficulty: Astra targets the hardest end-to-end tasks, while Sol balances strong reasoning with everyday cost, with enhanced coding, math, and agentic workflows

From $0.0025 /1M tokens

OpenAI

GPT 5.6

OpenAI's tiered large model series (Sol/Terra/Luna), focused on coding, complex reasoning, and cybersecurity, with models selectable along the performance and cost curve

From $0.005 /1M tokens

Anthropic

Claude 5.5

The Claude 5.5 series includes three tiers—Opus, Sonnet, and Haiku—which can be chosen based on task complexity and cost, covering agentic coding, computer use, and high-concurrency batch processing

From $0.100 /1M tokens

Anthropic

Claude 4.8

A general-purpose text model for enterprise long-horizon agents, coding, and deep reasoning, with a strength in maintaining task consistency across multi-turn complex workflows

From $0.229 /1M tokens

Google

Veo 3.1

Google's video generation model: image input can natively generate 8-second videos with ambient sound and dialogue, supporting up to 4K while keeping the subject's appearance consistent

From $0.290 /second

Google

Veo 3.1 Lite

Google's low-cost, high-throughput video generation tier, with speed on par with Veo 3.1 Fast, supporting image-to-video, multiple aspect ratios, and durations

From $0.060 /second

MiniMax

Hailuo 2.3

A video generation model launched by MiniMax that supports both text-to-video and image-to-video, with improvements over the previous generation in anime-style consistency, full-body motion rendering, and the realism of subtle facial expressions, making it suitable for anime shorts and live-action-feel commercial videos

From $0.270 /video

Alibaba

Wan 2.7 Image

An image generation and editing model launched by Alibaba that integrates text-to-image, multi-reference image composition, and instruction-based editing into a single workflow, with support for long-text rendering and brand color control

From $0.035 /image

ByteDance

Seedream 5.0

ByteDance's production-grade image generation model, supporting web retrieval and multi-step logical reasoning, 4K output, and example-based editing, suitable for product images and infographic creation

From $0.025 /image

Recraft

Recraft V4.1

A production-oriented model for generating design assets, with native editable SVG vector output. It reliably produces images from short prompts and is well suited to icons, typography, and brand illustrations.

From $0.010 /image

Alibaba

Qwen Image 3.0

Alibaba's third-generation image generation and editing model, skilled at dense layout and multilingual text rendering under long prompts, and supports reference-image editing

From $0.036 /image

Alibaba

Qwen Image 2.0

Alibaba's unified architecture model for image generation and editing, skilled at long-form Chinese text rendering, supporting instructions up to 1000 tokens and 2K output

From $0.042 /image

Moonshot AI

Kimi K3

Moonshot AI's open-weight frontier model with native support for text, image, and video understanding, a 1M-token context, and strong performance in long-horizon coding and iterative tool calling

From $0.232 /1M tokens

xAI

Grok 4

xAI's flagship reasoning model, with enhanced advanced reasoning, native tool calling, and real-time search, plus long-context and image input support, suited for highly complex reasoning and Agent applications

From $0.210 /1M tokens

DeepSeek

DeepSeek V4

A new generation of text model series, including Pro and Flash versions, supporting long context of up to one million tokens, designed for coding, reasoning, and agentic tasks

From $0.014 /1M tokens

Anthropic

Claude 4.6

Flagship text model with a 1M-token long context, positioned for deep reasoning, complex coding, and long-horizon autonomous agent tasks

From $0.300 /1M tokens

Luma

Ray 3.2

Luma's cinematic video generation model, with native support for HDR and EXR export, suited to atmospheric establishing shots, advertising, and early-stage concept films for film and television; prompt adherence is stable under structured shot instructions

From $0.214 /video

PixVerse

PixVerse V6

PixVerse's flagship video generation model, covering both text-to-video and image-to-video in a single model, with support for precise camera control, character performance, and reference image fusion, aimed at production-grade output

From $0.036 /second

Black Forest Labs

FLUX 1.1 Pro

Black Forest Labs' flagship text-to-image model, roughly 6 times faster than Flux.1 Pro with better prompt adherence, ideal for image generation at scale

From $0.050 /image

Alibaba

Z-Image

Alibaba Tongyi's open-source text-to-image model, built on a single-stream DiT architecture with roughly 6 billion parameters, excelling at Chinese and English text rendering and bilingual instruction following

From $0.008 /image

Alibaba

HappyHorse 1.0

A single generation jointly produces video and natively synchronized audio, supports multilingual lip sync and up to 1080p output in multiple aspect ratios, making it suitable for talking-head and dialogue-based short videos

From $0.168 /second

Black Forest Labs

FLUX.1 Schnell

Black Forest Labs' distilled text-to-image model, a 12-billion-parameter rectified flow transformer focused on low-latency fast image generation, suitable for batch creation of concept art and sketches

From $0.005 /image

Google

Nano Banana 2 Lite

A lightweight, efficiency-focused model in the Google image family, built for low latency and low cost, suited to rapid ideation and high-throughput image generation, and a seamless replacement for the first-generation Nano Banana

From $0.033 /image

MiniMax

MiniMax Music 3

Just input lyrics and a music description to generate a stereo song up to about 5 minutes long, complete with vocals and full song structure—ideal for quickly producing song demos and custom soundtracks.

From $0.0026 /second

MiniMax

MiniMax Music 2.6

A vocal-plus-instrumental model that generates complete songs from text, adding AI Cover-style adaptations and automatic lyric writing, with first output latency claimed to be under 20 seconds

From $0.210 /song

MiniMax

MiniMax Music 1.5

A text-to-music model that generates a complete song with vocals and accompaniment in one pass from a style description and lyrics, with each song up to about 4 minutes long and support for arranging sections using structural tags

From $0.070 /song

Google

Lyria 3 Pro

Google's advanced music generation model, capable of generating complete tracks of about 3 minutes in 48kHz stereo, understanding section structures such as intro, verse, and chorus, with better prompt adherence than Lyria 3

From $0.140 /song

Ideogram

Ideogram V4

An open-weight text-to-image model featuring multilingual text rendering and native 2K output, with support for JSON prompts and bounding-box layout control

From $0.050 /image

Alibaba

Wan 2.7 Video

Alibaba's WAN series video generation models support text-to-video, image-to-video, and reference-guided video, with multiple reference inputs maintaining character and product consistency across shots.

From $0.100 /second

Google

Veo 3.1 Fast

The image-to-video model in the Veo 3.1 series built for fast turnaround, generating picture and audio in sync, suited to finished-content production such as marketing, presentations, and social media

From $0.170 /second

ByteDance

Seedream 4.5

ByteDance's commercial-grade image model, featuring cinematic lighting, cross-shot character consistency, and multi-image reference editing, ideal for high-resolution outputs for e-commerce and marketing assets

From $0.045 /image

Google

Lyria 3.5

Google's flagship music generation model that first plans the structure of intro, verse, chorus, and so on, then generates a complete song with vocals and lyrics, supports singing in multiple languages, and can be called via the unified HiAPI.ai API

From $0.090 /song

HeyGen

HeyGen Avatar V

Build a reusable real-person avatar from a reference video of about 15 seconds, transfer its gestures and movements to new scripts and scenes, and maintain consistency across scenes

From $0.150 /second

851 Labs

851 Labs Background Remover

An image processing model focused on automatic cutout, capable of outputting transparent PNGs or masks, suitable for batch background removal from e-commerce product photos and portraits

From $0.002 /image

Kuaishou

Kling 3.0 Turbo

A video generation model built for fast previews and high-frequency iteration, supporting both text-to-video and image-to-video, producing clips of 1–15 seconds at 480p–1080p, with image-to-video referencing up to 7 images

From $0.130 /second

xAI

Grok Imagine Quality

xAI's high-fidelity image generation and editing model, with more stable text rendering and composition, supporting 1K/2K output and consistent editing with reference images

From $0.070 /image

xAI

Grok Imagine Image 2.0

xAI's image generation and editing model, with strong instruction following and complex layout rendering, supports iterative image editing with reference images, and can output 1K/2K images in multiple aspect ratios

From $0.052 /image

Black Forest Labs

FLUX.2 Klein 9B

A 9-billion-parameter rectified-flow image model, step-distilled to 4 steps, unifying text-to-image and single/multi-reference image editing in a compact architecture, aimed at low-latency real-time generation scenarios

From $0.0086 /image

Black Forest Labs

FLUX.2 Klein 4B

A 4-billion-parameter distilled small model that unifies text-to-image generation and image editing, with end-to-end inference as fast as under 1 second and runs on about 13GB of VRAM

From $0.0004 /image

Black Forest Labs

FLUX.2

Black Forest Labs' family of image generation and editing models, supporting reference-image-based style transfer and multi-reference image fusion, while preserving the original composition and subject placement as much as possible during editing

From $0.035 /image

Black Forest Labs

FLUX 3 Image

An image-oriented model in the Black Forest Labs multimodal family, sharing a joint training architecture and the Self-Flow framework with video and audio, suitable for upgrading image generation pipelines built on the FLUX system

From $0.041 /image

Meta

Muse Image 1.0

Meta's reasoning-based image generation and editing model that first breaks down complex prompts before rendering, can fuse multiple reference images, and leverages web retrieval to ensure factual accuracy

From $0.015 per task

MiniMax

MiniMax H3

A unified multimodal video model that handles text, images, video, and audio within a single context, supporting text-to-video, image-to-video, reference-to-video, and instruction-based editing, and can generate synchronized audio

From $0.072 /second

HeyGen

HeyGen Avatar IV

Upload a single photo plus a script to generate a talking avatar video with lip sync, facial expressions, and gestures, supporting 1280p+ output, ideal for digital presenters and voiceover content

From $0.150 /second

Alibaba

HappyHorse 1.1

Alibaba video generation model; a single model covers text-to-video, image-to-video, and reference-image-to-video, supports 1080p and 3–15 second clips, and fuses multiple reference images to strengthen character consistency, making it suitable for multi-shot storytelling and e-commerce advertising assets

From $0.160 /second

xAI

Grok Imagine

xAI's creative generation model, supporting image-to-image editing and style guidance, with up to 9 reference images to control composition and characters; called through the unified HiAPI.ai interface

From $0.011 /second

ElevenLabs

ElevenLabs

A speech and audio generation family built for developers, covering text-to-speech, conversational speech, sound effects, and music generation

From $0.0029 /second

Alibaba

Wan 2.6 Flash

A speed-optimized image-to-video version of the Wan 2.6 series, with lower cost and faster output, suitable for draft exploration and high-frequency batch generation, though its visual refinement is not on par with the standard version

From $0.043 /second

Krea

Krea 3

Supports text generation and reference-image editing, native 2K output, roughly 8 seconds per edit, suited for high-frequency visual iteration and asset reuse

From $0.036 /image

Krea

Krea 2 Medium Turbo

The speed-first distilled and accelerated version in the Krea 2 series, with low per-image billing cost, suitable for rapid iteration and design concept exploration

From $0.021 /image

Google

Gemini Omni 1.1 Flash

A multimodal model for video generation and editing, with a single API covering text-to-video, image-to-video, reference-image-to-video, and video editing, layered output from draft to 4K with a built-in audio track

From $0.450 /video

Creatify

Creatify Boreal

A low-cost video generation model for batch variants of ad creatives, supporting text-to-video, image-to-video, and photo-plus-audio generation of multilingual talking videos, with fast output

From $0.015 /second

Google

Google Virtual Try-On

Upload a full-body photo to generate a try-on image of the specified clothing; diffusion-based technology simulates fabric folds and lighting to help with online clothing purchase decisions

From $0.107 /image

Google

Gemini 3.1 Flash TTS

Low-latency text-to-speech model that controls voice, speaking rate, and accent using audio tags embedded in the text, supports over 70 languages, and is accessed through the unified HiAPI.ai interface

--

Black Forest Labs

FLUX.1 Fill Pro

A professional-grade local inpainting and outpainting model that replaces, removes, or extends parts of an image at precise points according to a binary mask while keeping lighting and perspective consistent; it requires a mask input and is suited for retouching rather than whole-image generation

From $0.071 /image

FASHN

FASHN Tryon v1.6

Virtual try-on model: input a person image and a garment image to generate the model wearing the outfit, with native 864x1296 output, flat-lay image input support, and three quality modes

From $0.107 /image

Recraft

Recraft Crisp Upscale

A lightweight AI image upscaler that balances denoising with detail preservation while upscaling, at low per-use cost, making it ideal as a final sharpening step in design workflows

From $0.004 /image

Vidu

Vidu Q4 Preview

The first publicly available preview of the Vidu Q4 series, focused on character performance and native audio, supporting reference guidance from up to 15 images and 3 audio clips, and outputting video at up to 4K

From $0.051 /second

Lightricks

LTX 2.5 Fast

Lightricks' accelerated video generation model supports text-to-video and image-to-video, generating visuals and audio in sync, ideal for rapid output and prototype validation

From $0.086 /second

Runway

Runway Gen 4.5

Upon release, it ranked first on the Artificial Analysis text-to-video leaderboard with 1247 Elo, showing outstanding prompt adherence, physics, and human motion, making it well suited for film storyboarding and brand short films

From $0.172 /second

Recraft

Recraft Creative Upscale

Generative image upscaling that increases resolution while redrawing and supplementing textures, details, and facial features—ideal for turning low-resolution assets into high-resolution finished products

From $0.357 /image

Alibaba

Qwen Image 2.1

A unified image model for text-to-image generation and image editing, with native support for 2K resolution and RGBA output with a real alpha channel, allowing multiple edit regions to be specified using circles, hand-drawn annotations, or masks

From $0.020 /image

Mureka

Mureka 9.5

A music generation model with more restrained arrangements and more open space, closely following the prompt's genre, instrumentation, and mood, with more natural vocals; supports both instrumental-only and lyrics-to-song modes

From $0.322 per request

Mirelo AI

Mirelo SFX 2.0

An audio output model for sound effect generation scenarios, suitable for producing and batch-iterating sound effect assets for content such as videos and games

From $0.021 /second

Kuaishou

Kling AI Avatar

Audio-driven digital human talking video generation; a single image plus speech is enough to output a lip-synced video, supporting continuous generation of about 5 minutes, with the Standard version at up to 720p

--

Kuaishou

Kling 3.0

A unified multimodal video generation series supporting text-to-video, image-to-video, reference-to-video, and in-video editing, with native lip sync and multilingual audio

From $0.100 /second

Kuaishou

Kling 2.5

An image-to-video model launched by Kuaishou, standing out for its smooth motion and character consistency, with support for negative prompts and CFG adjustment, making it suitable for generating short clips with highly dynamic camera work

From $0.060 /second

Google

Imagen 4

Google's text-to-image series, focused on in-image text rendering and complex lighting, offering Fast, Standard, and Ultra tiers that trade off quality against cost

From $0.030 /image

Ideogram

Ideogram V4.5

An image generation and editing model excelling at clear typography and precise multi-turn local edits, with native 2K output, ideal for posters, logos, and packaging design

From $0.011 /image

Ideogram

Ideogram V3 Character

Lock the same character using a reference image, keep the face and clothing consistent across changes in scene, pose, and lighting, and carry forward Ideogram's strength in in-image text layout

From $0.090 /image

xAI

Grok Imagine 1.5 Lite

A lightweight, low-cost video generation tier that supports text-to-video and image-to-video, generating sound effects and dialogue in the same pass, suited for high-frequency batch production of short clips

From $0.029 /second

Google

Gemini Omni

Google's multimodal video generation and editing model, supporting combined image, text, audio, and video inputs, and allowing iterative adjustment of shots and details through natural language conversation

--

Black Forest Labs

FLUX 3 Video

Black Forest Labs' first video model, built on a unified multimodal architecture, supporting text-to-video, image-to-video, and keyframe continuation, with visuals and native audio generated in sync, up to about 20 seconds of HD per generation

From $0.090 /second

Black Forest Labs

FLUX 3 Max

A video generation model that supports text-to-video and image-to-video, focused on low-latency, fast turnaround; public benchmarks report roughly 11–12 seconds to generate a 10-second clip, making it well suited to creative iteration and short-video assets

From $0.061 /second

Bria

FIBO 1.5

BRIA's 8B flow-matching DiT distilled image model generates images with just 4 to 6 sampling steps and supports JSON-structured prompts with attribute-decoupled editing

From $0.058 /image

Bria

BRIA Product Shot

An image editing model for e-commerce product photos that naturally places products into scene backgrounds generated from text or reference images, while preserving texture and brand details

From $0.058 /image

Bria

BRIA Eraser

An image editing model focused on mask erasure and region reconstruction. It removes target objects according to a black-and-white mask and completes the image. Trained on authorized data, it is suitable for batch cleanup of e-commerce and marketing assets.

From $0.058 /image