Modele AI

Çdo model kryesor AI. Një platformë.

AI që ndërton sajtin tënd ekzekutohet mbi Claude Opus 5.5 nga Anthropic. Dhe çdo aplikacion që krijon mund të përdorë 256 modele të tjera për bisedë, imazhe, video, zë, përkthim dhe kërkim, pa asnjë çelës API.

256

modele

45

ofrues

15

aftësi

Si funksionon AI te Mjegulla

Dy shtresa: AI që ndërton për ty, dhe AI që aplikacionet e tua mund të përdorin.

Ndërtuesi

Kur përshkruan një sajt ose një aplikacion, një agjent AI e planifikon, shkruan kodin dhe tekstin, kontrollon pamjen paraprake për gabime dhe rregullon çfarë gjen. Ti zgjedh sa fort mendon për çdo mesazh.

I shpejtë

Redaktime të shpejta dhe ndryshime të vogla

I balancuar

Modeli i duhur i zgjedhur për çdo detyrë

Më e mira

Modeli më i aftë për ndërtime të mëdha

  • Claude Opus 5.5Planifikon dhe ndërton sajte dhe aplikacione të mëdha
  • Claude Sonnet 5.5Shkruan dhe redakton kod
  • Claude Haiku 4.5Kontrolle të shpejta dhe ndryshime të vogla
  • Kimi K2.7Motor alternativ ndërtimi për ekzekutime të gjata agjentike

Modaliteti Plan i lejon agjentit të propozojë një plan para se të ndërtojë.

AI brenda aplikacioneve të tua

Kërkoji AI Studio një chatbot, një gjenerues imazhesh ose një veçori zëri dhe ai lidh modelin e duhur në aplikacionin tënd. Përdorimi paguhet me kredite dhe ti cakton kufij shpenzimi ditorë dhe mujorë.

  1. 1Zgjidh një model nga skeda e modeleve AI në Studio, ose përmende direkt në bisedë.
  2. 2Agjenti e lidh atë: pa çelësa API, pa llogari ofruesish.
  3. 3Shiko çdo thirrje dhe koston e saj në regjistrin e përdorimit AI.

15 aftësi

Katalogu i modeleve

Kërko dhe filtro çdo model të disponueshëm për aplikacionet e tua.

30 modele

Veo 3.1 Fast

Google

A faster version of Veo 3.1 optimized for lower latency while maintaining high-quality video and audio output.

Gjenerim videosh @veo-3.1-fast

Veo 3.1

Google

Google's latest video generation model with improved quality, motion, and audio generation.

Gjenerim videosh @veo-3.1

Grok Imagine Video

xAI

xAI's video generation model. Generates, edits, and extends videos from text and image inputs with native synchronized audio including dialogue, sound effects, and music. Supports multiple creative modes (normal, fun, custom).

Gjenerim videosh @grok-imagine-video

Gen 4.5

Runway

RunwayML's video generation model supporting both text-to-video and image-to-video with customizable duration, aspect ratio, and content moderation controls.

Gjenerim videosh @gen-4.5

Aleph 2

Runway

RunwayML's video editing model. Edit one frame to update your whole video, make changes across multiple shots, and work with up to 30 seconds of video. Supports keyframe-guided editing for precise control over specific moments in the clip.

Gjenerim videosh @aleph-2

Hailuo 2.3 Fast

MiniMax

A lower-latency version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization while enabling faster iteration.

Gjenerim videosh @hailuo-2.3-fast

Hailuo 2.3

MiniMax

A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across text-to-video and image-to-video workflows.

Gjenerim videosh @hailuo-2.3

H3 Max

MiniMax

A fast multimodal video generation model supporting text-to-video and image-to-video generation at 480P and 768P.

Gjenerim videosh @h3-max

H3 Lite

MiniMax

A lightweight multimodal video generation model supporting text-to-video, first and last frame image-to-video, and reference-to-video generation at 480P and 768P.

Gjenerim videosh @h3-lite

H3 Highspeed

MiniMax

A multimodal video generation model that balances quality and speed, supporting text-to-video, first and last frame image-to-video, and reference-to-video generation at 768P.

Gjenerim videosh @h3-highspeed

H3

MiniMax

A multimodal video generation model supporting text-to-video, first and last frame image-to-video, and reference-to-video generation with 768P and 2K output.

Gjenerim videosh @h3

Seedance 2.0 Mini

ByteDance

ByteDance's compact, cost-efficient video generation model from the Seedance 2.0 family. Supports text-to-video, image-to-video, reference video, and reference audio for background music. Ideal for high-volume workloads where speed and cost matter.

Gjenerim videosh @seedance-2.0-mini

Seedance 2.0 Fast

ByteDance

Faster variant of ByteDance's Seedance 2.0 video model. Trades some quality for speed while sharing the same multimodal architecture. Supports text-to-video, image-to-video, native audio generation, multimodal references (images, videos, audio), video editing, and video extension.

Gjenerim videosh @seedance-2.0-fast

Seedance 2.0

ByteDance

ByteDance's next-generation video model with a unified multimodal architecture. Generates high-quality video with synchronized audio from text, images, video clips, and audio inputs. Supports multimodal references (up to 9 images, 3 videos, 3 audio files), native audio generation, video editing, video extension, intelligent duration, and adaptive aspect ratio.

Gjenerim videosh @seedance-2.0

Seedance 1 Pro Fast

ByteDance

A speed- and cost-optimized variant of Seedance 1.0 Pro, delivering roughly 30-60% faster inference at about 60% lower cost while keeping the same capability surface. Suited to rapid iteration, storyboarding, and platform-scale video workloads.

Gjenerim videosh @seedance-1-pro-fast

Seedance 1 Pro

ByteDance

ByteDance's first-generation cinematic video model. Generates 1080p video from text or images with strong prompt adherence, stable motion, and native multi-shot narrative coherence. Supports first/last-frame image-to-video and image references.

Gjenerim videosh @seedance-1-pro

Wan 3.0 Prime

Alibaba

Alibaba's Wan 3.0 Prime text-to-video model. Generates cinematic videos from text prompts with adaptive aspect ratio, 480P, 720P, or 1080P resolution, and configurable duration.

Gjenerim videosh @wan-3.0-prime

Wan 3.0

Alibaba

Alibaba's Wan 3.0 text-to-video model. Generates cinematic videos from text prompts with adaptive aspect ratio, 480P, 720P, or 1080P resolution, and configurable duration.

Gjenerim videosh @wan-3.0

v6

PixVerse

Pixverse v6 is the latest Pixverse video model with support for up to 15-second videos, customizable duration from 1 to 15 seconds, and audio generation.

Gjenerim videosh @v6

v5.6

PixVerse

Pixverse v5.6 is a video generation model supporting text-to-video and image-to-video with audio generation, customizable aspect ratios, and up to 1080p output.

Gjenerim videosh @v5.6

Q3 Turbo

Vidu

Vidu Q3 Turbo is a faster version of Vidu Q3 optimized for lower latency video generation while maintaining audio support and up to 16-second clips.

Gjenerim videosh @q3-turbo

Q3 Pro

Vidu

Vidu Q3 Pro is a high-quality video generation model supporting text-to-video, image-to-video, and start/end-frame-to-video workflows with audio and up to 16-second clips.

Gjenerim videosh @q3-pro

P Video

Pruna AI

Pruna's P-Video is a premium video generation model supporting text-to-video, image-to-video, and audio-conditioned generation up to 1080p at 24 or 48 fps, with configurable duration up to 20 seconds.

Gjenerim videosh @p-video

Ltx 2 5 Fast

Lightricks

llightricksText-to-Video Lightricks LTX-2.5 Fast is a fast video generation model for text-to-video and image-to-video workflows, with synchronized audio, configurable duration, resolution, and frame rate.

Gjenerim videosh @ltx-2-5-fast

Ltx 2 3 Pro

Lightricks

llightricksText-to-Video Lightricks LTX-2.3 Pro is a high-fidelity video generation model for text-to-video and image-to-video, with synchronized audio, first-to-last frame control, and portrait and landscape output up to 4K, in 6, 8 or 10 second clips.

Gjenerim videosh @ltx-2-3-pro

Ltx 2 3 Fast

Lightricks

llightricksText-to-Video Lightricks LTX-2.3 Fast is a low-cost video generation model for text-to-video and image-to-video, with synchronized audio, first-to-last frame control, portrait and landscape output up to 4K, and clips up to 20 seconds.

Gjenerim videosh @ltx-2-3-fast

Kling v4 Flash

Klingai

Kling 4.0 Flash is Kling AI's fast text-to-video model, producing 3 to 20 seconds of 720p video from prompts of up to 26,000 characters.

Gjenerim videosh @kling-v4-flash

Kling v4

Klingai

Kling 4.0 is Kling AI's video generation model for text-to-video and multi-keyframe image-to-video, producing up to 30 seconds of 720p or 1080p video from prompts of up to 26,000 characters and up to 10 keyframes.

Gjenerim videosh @kling-v4

Hh1.1 T2v

Alibaba

Alibaba's HappyHorse 1.1 text-to-video model. Generates videos from a text prompt with stronger dynamic expressiveness, better visual quality, and improved instruction following over 1.0. Configurable resolution, aspect ratio, and duration (3-15s).

Gjenerim videosh @hh1.1-t2v

Hh1 T2v

Alibaba

Alibaba's HappyHorse 1.0 text-to-video model. Generates videos from a text prompt with configurable resolution, aspect ratio, and duration (3-15s).

Gjenerim videosh @hh1-t2v

Ndalo së planifikuari. Fillo të shesësh.

E vetmja gjë midis teje dhe klientit tënd të parë është një fjali dhe pak minuta.

20 kredite AI falas për të filluar · Anulo kur të duash