Agents work on a computer of their own that keeps your files and progress, choose from 900+ models, and bring team permissions and audit logs for business.

AI that finishes the work, not just the answer

Claude Fable 5.1GPT ImageMiniMax H3 TurboOmniVoiceTRELLIS.2 4B (3D Generation)
Sign in or sign up Continue with Google Pricing AI model lineup
Chats move to Agents, GPT-6 Luna by default, and workspaces for teams
Trusted by 758K+ users in 236 countries.
Popular now

Trending

MiniMaxMiniMax H3 Turbo
VideoKostenlos · 2 pro TagAfter allowance · ≈ $0.22–0.275/Nutzung
Input → output
text / image / video / audio → video / audio
Released
Jul 31, 2026
Capabilities
Text to video and stereo audio · First/end frame guidance · Control video · Injected keyframes · Soundtrack guidance · Control-video audio reuse · Audio generation from control video · Sliding-window continuation · Optional AI 2× upscale · Optional faster step skipping
Output
Video + stereo audio
Resolution
480p · 576p · 736p · optional 2× upscale
Duration
4.5–20 sec

Fast MiniMax H3 video model for synchronized video and stereo-audio generation with first/end frames, control video, keyframe injection, soundtrack guidance, and long-window continuation.

LightricksLTX-2.5 Distilled
VideoKostenlos · 2 pro TagAfter allowance · ≈ $0.0413/Sek. (auf Basis von 4s)
Input → output
text / image / video / audio → video / audio
Released
Aug 11, 2026
Capabilities
Native multi-shot story · Two-stage quality · Automatic duration · Diffusion video decoder · Video extension · Ingredients · Inpainting · Outpainting · First/end frames · Exact keyframes · Pose control · Depth control · Canny control · Raw video control
References
First/end frames · keyframes · control video
Resolution
480p · 540p · 720p · 1080p
Duration
1–20 sec

Fast LTX-2.5 synchronized audio-video generation with first/end frames, exact keyframes, video extension, soundtrack guidance, and control video.

Black Forest LabsFLUX.1 Schnell
ImageKostenlos · 4 alle 2 StundenAfter allowance · ≈ $0.0033/Bild
Input → output
text / image → image
Released
Aug 1, 2024
Capabilities
Fast generation · Prompt adherence · Variations
Resolution
512–2048 px
Formats
PNG · JPG · WEBP
References
Up to 1 image

Fast FLUX image model for quick text-to-image drafts, variations, and lightweight edits.

KREAKREA 2 Turbo
ImageKostenlos · 4 alle 2 StundenAfter allowance · ≈ $0.022/Bild
Input → output
text / image → image
Released
May 12, 2026
Capabilities
Identity editing · Character sheets · Inpainting · Outpainting
Resolution
512–2048 px
Formats
PNG · JPG · WEBP
References
Up to 2 images

Fast aesthetic image generation, identity-aware editing, character sheets, inpainting, and outpainting with KREA 2 Turbo.

Black Forest LabsFLUX.2 [klein] 9B
ImageKostenlos · 2 pro StundeAfter allowance · ≈ $0.000858–0.00372/Bild
Input → output
text / image → image
Released
Jan 23, 2026
Capabilities
Edit
References
Up to 4 images
Resolution
128–2048 px
Formats
JPG · PNG · WEBP

Balanced FLUX.2 image model for prompt accuracy, editing, references, and fast production use.

Soul AISoulX FlashHead (Talking Head)
VideoKostenlos · 3 pro TagAfter allowance · ≈ $0.055/Nutzung
Input → output
text / image / audio → video
Released
Feb 12, 2026
Capabilities
Talking head · Lip sync · Voice cloning
Input
Face image + Audio/Speech
Formats
MP4 (Talking Head Video)

Real-time talking-head model that animates a face image with speech and accurate lip sync.

Video

MiniMaxMiniMax H3 Turbo
VideoKostenlos · 2 pro TagAfter allowance · ≈ $0.22–0.275/Nutzung
Input → output
text / image / video / audio → video / audio
Released
Jul 31, 2026
Capabilities
Text to video and stereo audio · First/end frame guidance · Control video · Injected keyframes · Soundtrack guidance · Control-video audio reuse · Audio generation from control video · Sliding-window continuation · Optional AI 2× upscale · Optional faster step skipping
Output
Video + stereo audio
Resolution
480p · 576p · 736p · optional 2× upscale
Duration
4.5–20 sec

Fast MiniMax H3 video model for synchronized video and stereo-audio generation with first/end frames, control video, keyframe injection, soundtrack guidance, and long-window continuation.

LightricksLTX-2.5 Distilled
VideoKostenlos · 2 pro TagAfter allowance · ≈ $0.0413/Sek. (auf Basis von 4s)
Input → output
text / image / video / audio → video / audio
Released
Aug 11, 2026
Capabilities
Native multi-shot story · Two-stage quality · Automatic duration · Diffusion video decoder · Video extension · Ingredients · Inpainting · Outpainting · First/end frames · Exact keyframes · Pose control · Depth control · Canny control · Raw video control
References
First/end frames · keyframes · control video
Resolution
480p · 540p · 720p · 1080p
Duration
1–20 sec

Fast LTX-2.5 synchronized audio-video generation with first/end frames, exact keyframes, video extension, soundtrack guidance, and control video.

xAIGrok Imagine Video 1.5
VideoUpgrade erforderlich
Input → output
text / image → video
Released
May 30, 2026
Capabilities
Audio
References
Up to 7 images
Resolution
480p · 720p · 1080p
Duration
1–15 sec

Grok video model for high-quality 480p, 720p, and 1080p video generation from text or first-frame image.

GizAIVideo Upscale & Enhance
VideoKostenlos · 1 alle 6 StundenAfter allowance · ≈ $0.11/Nutzung
Input → output
video → video
Released
Jul 3, 2024
Capabilities
Upscale · Denoise · Deblur
Output
HD · FHD · 2K · 4K
Processing
AI enhancement

Upscale, clean up, sharpen, or resize an existing video with AI or standard processing.

GizAIVideo Interpolate
VideoKostenlos · 1 alle 6 StundenAfter allowance · ≈ $0.088/Nutzung
Input → output
video → video
Released
Jul 3, 2024
Capabilities
Frame interpolation · Motion smoothing
Frame rate
2x · 3x · 4x
Quality
Fast · Balanced · Quality

Increase video frame rate with frame interpolation.

Soul AISoulX FlashHead (Talking Head)
VideoKostenlos · 3 pro TagAfter allowance · ≈ $0.055/Nutzung
Input → output
text / image / audio → video
Released
Feb 12, 2026
Capabilities
Talking head · Lip sync · Voice cloning
Input
Face image + Audio/Speech
Formats
MP4 (Talking Head Video)

Real-time talking-head model that animates a face image with speech and accurate lip sync.

3D

MicrosoftTRELLIS.2 4B (3D Generation)
3DKostenlos · 1 pro TagAfter allowance · ≈ $0.0099–0.0296/Nutzung
Input → output
image → 3D
Released
Dec 17, 2025
Formats
GLB

Image-to-3D model that converts a source image into a textured 3D asset preview.

TripoTripo 3D v3.1
3D≈ $0.33–0.55/Nutzung
Input → output
text → 3D
Released
Feb 11, 2026
Price
≈ $0.33–0.55/Nutzung
Formats
GLB · FBX

High-fidelity 3D asset generation with enhanced geometry and texture precision

TencentHunyuan 3D 3.1 Pro
3D≈ $0.413–0.907/Nutzung
Input → output
text → 3D
Released
Feb 10, 2026
Price
≈ $0.413–0.907/Nutzung
Formats
GLB

High-fidelity 3D asset generation with multi-view reconstruction and PBR materials

TencentHunyuan 3D 3.1 Rapid
3D≈ $0.248–0.413/Nutzung
Input → output
text / image → 3D
Released
Feb 10, 2026
Price
≈ $0.248–0.413/Nutzung
Formats
GLB

Fast 3D asset generation optimized for rapid prototyping and iteration

MeshyMeshy-6
3D≈ $0.88/Nutzung
Input → output
text / image → 3D
Released
Jan 18, 2026
Price
≈ $0.88/Nutzung
Formats
GLB

High-fidelity 3D generation with cleaner geometry, low-poly workflows, and production-ready mesh control

MetaSAM 3D Objects
3D≈ $0.00561–0.0099/Nutzung
Input → output
text / image → 3D
Released
Nov 19, 2025
Price
≈ $0.00561–0.0099/Nutzung
Formats
GLB

Single-image 3D reconstruction for objects and scenes