AI models
AI image, video and voice models, tested
One page per model: what it costs, what the free tier really gives you, which settings matter and what they look like, and the same prompts run through every model so you can compare real output. Twelve pictures for every image model, nine clips for every video model, four scripts for every voice model. Each picture below is the model drawing itself.
Compared
The same prompts across every model, ranked with a verdict, and the pairs people ask about.
The best AI image generator, tested
Twelve prompts through 36 AI image models, from Nano Banana, GPT Image and FLUX to Krea, Meta and Microsoft, every picture kept. Prices, speed and a verdict per prompt.
The best AI video generator, tested
The same nine prompts through 30 AI video models, Veo, Kling, Seedance, FLUX, Sora, Wan, Hailuo, MiniMax and more, every clip kept. Prices, waits and a verdict per prompt.
One prompt, every image model

Text in an image
Which AI image model renders text best

Product on white
Which AI image model makes the best product shot on white

Face and hands
Which AI image model does faces and hands best

Logo mark
Which AI image model makes the best logo

Busy scene
Which AI image model handles a busy scene best

Specific art style
Which AI image model holds an art style

Chart
Which AI image model draws an accurate chart

Wide aspect ratio
Which AI image model makes the best wide banner

Infographic with steps
Which AI image model makes the best infographic

Food photography
Which AI image model makes the best food photo

Hard composition
Which AI image model follows a hard composition

Edit an existing image
Which AI image model edits a picture best
One prompt, every video model

Product turntable
Which AI video model makes the best product turntable

Person speaking
Which AI video model makes the best talking head

Animated title card
Which AI video model can render text on screen

Camera move
Which AI video model handles a camera move best

Physics
Which AI video model gets physics right

Hands at work
Which AI video model handles hands and objects best

Busy scene
Which AI video model handles a busy scene best

Specific art style
Which AI video model holds an art style

Image to video
Which AI image-to-video model keeps the product intact
Head to head
Image models
Every image model that works from a prompt runs the same 12 prompts; editing models run a fixed set of edits.
Bria
Black Forest Labs

FLUX 3 Image
$0.048 per 1k image, about 1 megapixel via BFL API
Black Forest Labs' October 2026 image model: native 2K and 4K, up to 10 references, one flat price per image by size.

FLUX 3 Image Klein
$0.009 per 1k image via BFL API
Black Forest Labs' small open-weights FLUX 3: about a cent a 1K image, three seconds a picture, and a clean, one-pass product edit.

FLUX.2 Pro
$0.03 per 1k image via BFL API
Black Forest Labs' production model: 3 cents a megapixel, photoreal, no knobs to tune.

FLUX.2 Flex
$0.05 per 1k image via BFL API
The FLUX.2 tier with knobs: steps and guidance you can tune, better typography, 5 cents a megapixel.

FLUX.2 Max
$0.07 per 1k image via BFL API
The top FLUX.2 tier: 7 cents a megapixel for BFL's most realistic and precise output and edits.
OpenAI

GPT Image 2.6 Flare
Clean text, transparency, careful edits and quick GIFs.

GPT Image 2.6 Sunburst
Intricate hero art, showcase GIFs and demanding revisions, slower.

GPT Image 2.5 Flare
$30.00 per per million image output tokens via OpenAI API
OpenAI's fast default since September 2026: GPT Image 2's tricks, faster, and a quarter of the price at high quality.

GPT Image 2.5 Sunburst
$30.00 per per million image output tokens via OpenAI API
OpenAI's precision tier: same prices as Flare, slower, built for edits where fidelity to the original matters most.

GPT Image 2
$30.00 per per million image output tokens via OpenAI API
The model behind ChatGPT's image generator from April to September 2026: exact sizes, cut-outs, precise edits, slow at high quality.
xAI
HiDream.ai
Ideogram

Ideogram 4.5
Ideogram's edit-first update: a flat price per image at any size, text that held at every quality tier, and edits that leave the rest of the picture alone.

Ideogram 4.5 Precise Edit
$0.06 per edit, medium quality via Ideogram API
Ideogram's region editor: change one area of a photo up to 8192 by 8192 at its original pixels, from $0.008 an image, and get the rest back as sent.

Ideogram 4.0
Ideogram's first open-weight model: built for design and type, three rendering speeds from under a cent a megapixel.

Ideogram Vector
Generate editable SVG graphics from a prompt, or convert an existing image to SVG with default and simple modes.
Krea

Krea 3
$0.06 per 2k image via Krea API
Krea's October 2026 model: native 2K, the most photographic results in this batch, a clean edit, and much slower in our runs than Krea advertises.

Krea 2 Medium
Krea 2 Medium is the smaller hosted Krea 2 image model.

Krea 2 Large
Krea 2 Large is the higher-priced hosted Krea 2 image model.
Microsoft

MAI-Image-2.5
$47.00 per million image output tokens via Microsoft Foundry
Microsoft's own image model: about five cents an image, strong photographs and scenes, small output and shaky small type.

MAI-Image-2.5 Pro
Microsoft's quality tier: cleaner type and a real handle on the edit, at about 17 cents for an image of one megapixel or less.
Meta
OpenMOSS
Google DeepMind

Nano Banana 2.1
$0.034 per 1k image via Gemini API
Google's October update to Nano Banana 2: thinking on by default, no 512px size, and about half the API price per 1K image.

Nano Banana 2
$0.067 per 1k image via Gemini API
Google's everyday model and the Gemini app default: near-Pro quality at Flash speed and half the price.

Nano Banana 2 Lite
$0.034 per 1k image via Gemini API
The cheapest and fastest Nano Banana: about $0.034 an image and a few seconds each, at a fixed 1K.

Nano Banana Pro
$0.13 per 1k or 2k image via Gemini API
Google's premium tier: the best at text and complex briefs, the slowest and dearest of the three.
Alibaba
Recraft

Recraft V4.1
$0.035 per raster image via Recraft API
Recraft's design-first model: brand colours as an input, real SVG in the vector variant, 3.5 cents an image.

Recraft V4.1 Flash
$0.007 per image via Recraft API
Recraft's cheapest model: 0.7 cents a raster image, a designer's eye for posters, and no styles, vector output or editing.

Recraft V3
$0.04 per raster image via Recraft API
Recraft's 2024 model, still on sale: 70 named styles, an image-to-image endpoint, 4 cents an image.
ByteDance

Seedream 5.0 Pro
ByteDance's flagship: reasons before it draws, text in 14 languages, dense layouts, under 7 cents at 1K.

Seedream 5.0 Lite
ByteDance's fast tier: 3.5 cents an image, 2K to 4K output, up to ten reference images.

Seedream 5.0 Flash
ByteDance's cheapest Seedream 5.0 tier: a flat price an image at 1K or 2K, about 15 seconds a picture, with an edit endpoint.

Seedream 4.5
ByteDance's late-2025 model: 4 cents an image, 2K and 4K, generation and editing in one model.
Video models
Every video model that works from a prompt runs the same 9 clips, five seconds each where the model allows it; editing models run a fixed set of clip edits.
Black Forest Labs
Google DeepMind

Gemini Omni Flash 1.1
Google's Omni Flash video model, version 1.1: 3 to 10 second clips with sound, from 360p drafts to 4K, $0.10 a second at 720p.

Gemini Omni Flash
$0.10 per second of 720p video via Gemini API
Google's conversational video model: 720p clips of 3 to 10 seconds with sound, edited by talking.
xAI
MiniMax

HeyGen Video
MiniMax H3 post-trained by HeyGen: 5 to 15 second clips with sound, $0.02 a second at 768p, the lowest price on our roster.

H3 Max Turbo
H3 Max Turbo is the lower-priced MiniMax H3 variant post-trained by fal.

H3 Max
MiniMax H3, post-trained by fal for prompt adherence and faster video generation.

MiniMax H3
MiniMax's July 2026 omni-modal model: native stereo sound, up to 2K and 15 seconds, open weights, from $0.05 a second.

Hailuo 2.3
MiniMax's October 2025 model at a flat price: $0.28 for six seconds at 768p, no audio, no settings to learn.
Alibaba
Kandinsky Lab
Kuaishou

Kling 4.0
$0.08 per output second at 720p, flash generation via Voyager credits
Kuaishou's October model: up to 30 seconds with stereo sound, per-shot prompts and up to 15 references, from $0.157 a second at 720p.

Kling 3.0 Standard
$0.14 per second at 720p, audio on via Kling app
Kuaishou's everyday tier: 15-second clips with audio, multi-shot storyboards, billed per second.

Kling 3.0 Pro
Kuaishou's higher-fidelity tier: the same 15-second, multi-shot envelope as Standard at $0.168 a second with audio.
Lightricks

LTX 2.5 Pro
$0.17 per second at 1080p via Voyager
Lightricks' quality tier of LTX 2.5, the open-weight audio and video model: 6 to 10 second clips with sound.

LTX 2.5 Fast
$0.13 per second at 1080p via Voyager
Lightricks' speed tier of LTX 2.5: 6 to 20 second clips with sound, up to 4K.

LTX 2.3
LTX 2.3 is Lightricks’ video model.
Luma AI
PixVerse
ByteDance

Seedance 2.0
ByteDance's February 2026 model: native audio, up to 15 seconds and 4K, about $1.50 for five seconds at 720p.

Seedance 2.5
ByteDance's July 2026 model: one continuous shot up to 30 seconds, 50 references, about $2.30 for five seconds at 720p.

Seedance 2.0 Mini
$0.061 per second at 720p via Voyager
ByteDance's low-cost tier of Seedance 2.0: 4 to 15 second clips with sound at 480p or 720p, half the token price of the full model.
OpenAI
Google DeepMind

Veo 3.1 Fast
Google's speed tier and the sensible default: the same audio, shapes and lengths as Veo 3.1 at $0.15 a second with sound.

Veo 3.1
Google's flagship: native audio, reference images, 4K, and the dearest per second here at $0.40 with sound.

Veo 3.1 Lite
Google's budget tier from March 2026: 720p and 1080p only, $0.05 a second with audio.
Alibaba

Wan 3.0
$0.10 per second at 720p via Alibaba Model Studio
Alibaba's August 2026 model: 2 to 30 seconds in one pass with audio, $0.10 a second at 720p, hosted only.

Wan 3.0 Prime
$0.14 per second at 720p via Voyager
The fast tier of Alibaba's Wan 3.0: 2 to 30 second clips with sound, at 40% more per second than standard.

Wan 2.7
$0.10 per second at 720p via Alibaba Model Studio
Alibaba's April 2026 model: 2 to 15 seconds with native audio and a thinking mode, $0.10 a second at 720p, hosted only.
Voice models
Every voice model reads the same 4 scripts, plain text with no vendor tags.
ElevenLabs
Eleven v4
$0.08 per 1,000 characters via ElevenLabs API
ElevenLabs' expressive model from 28 September 2026: audio tags, more than 90 languages, $0.08 per thousand characters, the same as v3 on ElevenLabs' API now.
Eleven v4 Turbo
$0.04 per 1,000 characters via ElevenLabs API
The low-latency sibling of Eleven v4, released the same day for voice agents: more than 90 languages, $0.04 per thousand characters.
Eleven v3
$0.08 per 1,000 characters via ElevenLabs API
ElevenLabs' expressive model, in general release since March 2026: audio tags for emotion, 70-plus languages, $0.08 per thousand characters on ElevenLabs' API.
Google DeepMind
Gemini 3.8 Flash TTS
$9.00 per million audio output tokens via Gemini API
Google's flagship voice model from 23 September 2026: style directions, two-speaker dialogue, 30 prebuilt voices, $9 per million audio tokens on the Gemini API.
Gemini 3.8 Flash Lite TTS
$6.00 per million audio output tokens via Gemini API
The cheaper tier of Google's Gemini 3.8 voice models, for dubbing and voice agents: the same controls as Flash, $6 per million audio tokens on the Gemini API.
Gemini 3.1 Flash TTS
$20.00 per million audio output tokens via Gemini API
Google's voice model: 30 voices, style directions in plain language, multi-speaker scripts, 80-plus languages, $20 per million audio tokens on Google's API.
HeyGen
HeyGen Voice
$0.03 per 1,000 characters via HeyGen API
HeyGen's own text-to-speech model from 9 October 2026: 24 library voices, cloning from a recording, 39 languages, $0.03 per thousand characters.
HeyGen Voice Turbo
The fast, low-cost tier of HeyGen Voice: the same voices, cloning and languages, the cheapest voice on this site.
hexgrad
MiniMax
More models Voyager runs
Every other model you can run on Voyager credits, with what it does and what it costs, from Voyager’s model catalog.
Image
MiniMax H3 Image
MiniMax · Create, Edit
2–7 credits an image on Voyager
Detailed stills up to 20 MP and edits from up to 16 references
MiniMax H3 Image Highspeed
MiniMax · Create, Edit
4–14 credits an image on Voyager
Quicker MiniMax H3 Image stills and edits
Seedream 5.5
ByteDance · Create, Edit
3–5 credits an image on Voyager
Posters and text-rich layouts, and edits from up to 10 references
Luma Uni-1
Luma · Create
1 credit an image on Voyager
Stills and edits that reason about your prompt
HiDream-O1
HiDream · Create
1 credit a megapixel on Voyager
Open model for detailed stills and edits
Recraft V4 Vector
Recraft · Create
8 credits an image on Voyager
Scalable SVG illustrations in your brand's style
Kling Image O3
Kuaishou · Create
3–6 credits an image on Voyager
Reference-guided images and edits up to 4K
Kling Image v3
Kuaishou · Create
from 3 credits an image on Voyager
Image generation and edits from Kling
Z-Image Turbo
Alibaba · Create
0.5 credits a megapixel on Voyager
Fast photoreal drafts
Topaz Precision Image Upscale
Topaz Labs · Upscale
8–16 credits an image on Voyager
Sharpens, restores and upscales stills
Bria FIBO 1.5
Bria · Create
4 credits an image on Voyager
Earlier FIBO; FIBO 2 replaced it
FLUX.2 Klein 4B
Black Forest Labs · Create
0.5 credits a megapixel on Voyager
Small, quick drafts
FLUX.1 Dev
Black Forest Labs · Create
2 credits an image on Voyager
Earlier open FLUX
FLUX.1 Schnell
Black Forest Labs · Create
0.3 credits a megapixel on Voyager
Very fast placeholder images
Topaz Image Upscale
Topaz Labs · Upscale
from 0.33 credits a megapixel on Voyager
Earlier Topaz image upscaling
Bria RMBG 2.0
Bria · Remove background
2–3 credits an image on Voyager
Clean subject cut-outs on a transparent background, trained on licensed data
Bria Guided Remove Background
Bria · Remove background
3 credits an image on Voyager
Background removal you steer with words: keep or drop named objects
Pixelcut Background Remover
Pixelcut · Remove background
2 credits an image on Voyager
Fast, high-quality cut-outs for product and e-commerce photos
Ideogram Remove Background
Ideogram · Remove background
1 credit an image on Voyager
Isolating subjects cleanly for compositing and reuse
Rembg Enhance
Smoretalk · Remove background
1 credit an image on Voyager
Matting-based cut-outs for vector art, 3D renders and photos
FeyNoBG
Feyn · Remove background
1 credit an image on Voyager
Inexpensive background removal for bulk cut-outs
Recraft Vectorize
Recraft · Vectorize
1 credit an image on Voyager
Turning a raster logo, icon or illustration into an editable SVG
Ideogram Vectorize
Ideogram · Vectorize
from 10 credits an image on Voyager
Converting an existing image to editable SVG without a prompt
Image2SVG
Visioncortex · Vectorize
1 credit an image on Voyager
Tunable raster-to-SVG tracing with control over detail and noise
Video
Seedance 2.5 Flash
ByteDance · Text to video, Image to video
6.8–15.2 credits a second on Voyager
Lower-cost Seedance for quick drafts, previews and social clips
Kling 4.0 Flash
Kuaishou · Text to video, Image to video
9.4–12.6 credits a second on Voyager
Lower-cost video from text, a first frame or references, and edits to your clips
OmniHuman 2
ByteDance · Image to video
10.5 credits a second on Voyager
A person who talks and moves, from one image and a voice
Vidu Q4
Shengshu · Image to video
4.5–39 credits a second on Voyager
Keeps characters consistent from reference images
FLUX.3 Video
Black Forest Labs · Text to video
17–47 credits a second on Voyager
Shots from text, images or keyframes, and edits and extensions to clips
HappyHorse 1.1
Alibaba · Text to video, Image to video
14–18 credits a second on Voyager
Shots from text, an image or references
Kling 3.0 Turbo
Kuaishou · Text to video, Image to video
from 14 credits a second on Voyager
Faster Kling clips from text or an image
Kling 3.0 Motion Control
Kuaishou · Edit video
16.8 credits a second on Voyager
Moves a character the way a recorded performance does
Seedance 2.0 Fast
ByteDance · Text to video, Image to video
from 13 credits a second on Voyager
Quicker Seedance for drafts
Bernini-R
ByteDance · Text to video
from 8 credits a second on Voyager
Generate video and edit images or footage with references
HeyGen Avatar 5
HeyGen · Text to video
10 credits a second on Voyager
A repeatable digital presenter
HeyGen Avatar IV
HeyGen · Image to video
10 credits a second on Voyager
A talking video from one portrait and a voice
Wan 2.2 VACE
Alibaba · Edit video
25–51 credits a video on Voyager
Repaint a masked object or region in your footage and keep everything else
Bria Video Eraser
Bria · Edit video
14 credits a second on Voyager
Erase a masked object or person from a short clip and keep everything else
VOID
Netflix · Edit video
5–10 credits a request on Voyager
Remove an object from your footage along with the shadows, reflections and knock-on motion it causes
PixVerse C1
PixVerse · Text to video
5–6.5 credits a second on Voyager
Cinematic clips with optional sound and reference images
PixVerse V6 Max
PixVerse · Text to video, Image to video
5.4–25.2 credits a second on Voyager
Higher-quality PixVerse V6 clips
Kling O3
Kuaishou · Edit video
from 16.8 credits a second on Voyager
Shots from text or images, and edits to your footage that keep its sound
VEED Dubbing
VEED · Dub
11 credits a second on Voyager
Translates video speech with lip-sync
VEED Dubbing Pro
VEED · Dub
18 credits a second on Voyager
Translates video speech with lip-sync, regional dialects and adjustable voice cloning
Topaz Precision Video Upscale
Topaz Labs · Upscale
10–60 credits a video on Voyager
Sharpens, restores and upscales footage, with generated detail if you like
Sync Lipsync 3
Sync Labs · Lip sync
800 credits a minute on Voyager
Matches the lips in footage or a portrait to new speech
SeedVR Upscale
ByteDance · Upscale
0.1 credits a megapixel on Voyager
Upscales footage with newly generated detail
HappyHorse 1.0
Alibaba · Text to video
14 credits a second on Voyager
Earlier HappyHorse; HappyHorse 1.1 replaced it
Grok Imagine Video
xAI · Text to video
5 credits a second on Voyager
Earlier Grok Imagine Video; 1.5 replaced it
Wan 2.6
Alibaba · Text to video
10–15 credits a second on Voyager
Earlier Wan, from text or an image
OmniHuman 1.5
ByteDance · Image to video
from 16 credits a second on Voyager
Earlier OmniHuman; OmniHuman 2 replaced it
Kling 2.5 Turbo Pro
Kuaishou · Text to video
7 credits a second on Voyager
Earlier Kling for quick, smooth motion
Topaz Video Upscale
Topaz Labs · Upscale
from 2 credits a second on Voyager
Earlier Topaz upscaling
SAM 3
Meta · Segment image, Segment image (mask data), Segment video, Segment video (mask data), Image embedding, Image to 3D, Image to 3D body, Align 3D
1–2 credits a request on Voyager
Masks and cut-outs of any object, by text, click or box, in images and video
SAM 3.1
Meta · Segment image, Segment image (mask data), Segment video, Segment video (mask data), Image embedding
1 credit a request on Voyager
Faster, sharper object masks and video tracking with stable object ids
SAM 2
Meta · Segment image, Segment image (mask data), Segment everything, Segment video, Segment video (mask data), Image embedding
1 credit a request on Voyager
Click-to-mask segmentation and video tracking; automatic masks of everything
Voice and audio
Eleven Music v2.5
ElevenLabs · Music
60 credits a minute on Voyager
Songs and instrumental beds with vocals, up to 10 minutes
Eleven Sound Effects v3
ElevenLabs · Sound effects
from 12 credits a minute on Voyager
Sound effects and loops from a description, several sounds in one prompt
Fish Audio S2.1 Pro
Fish Audio · Text to speech
1.5 credits per 1,000 characters on Voyager
Expressive voices, including featured creator voices
Lyria 3.5
Google · Music
10 credits a request on Voyager
Full songs with vocals and structure
Fish Audio Drama 3
Fish Audio · Text to speech
1 credit per 1,000 characters on Voyager
Dramatic, emotional performances
Qwen Audio 3 TTS Flash
Alibaba · Text to speech
from 4.5 credits a minute on Voyager
Fast multilingual speech with selectable voices
Seed Audio 1.0
ByteDance · Text to speech
from 18.8 credits a minute on Voyager
Performed speech in English and Mandarin, and sound effects
Seed Speech TTS v2
ByteDance · Text to speech
from 2.7 credits a minute on Voyager
Natural speech from ByteDance
Grok TTS v1
xAI · Text to speech
from 1.4 credits a minute on Voyager
Speech from text with xAI voices
MiniMax Speech 2.8 Turbo
MiniMax · Text to speech
from 5.4 credits a minute on Voyager
Quicker MiniMax speech
Chatterbox
Resemble AI · Text to speech
2.5 credits per 1,000 characters on Voyager
Copies a voice from a short sample to fix a line
Mureka 9.5
Mureka · Music
from 50 credits a request on Voyager
Full songs with vocals, or instrumentals
Eleven Music v2
ElevenLabs · Music
60 credits a minute on Voyager
Songs and instrumental beds
MiniMax Music 3
MiniMax · Music
from 12 credits a minute on Voyager
Songs with your lyrics and section tags, up to 5 minutes
Sonilo 1.1
Sonilo · Music, Sound effects
10.8–15 credits a minute on Voyager
Music and sound effects from a description
Stable Audio 3
Stability AI · Sound effects
4 credits a request on Voyager
Instrumental music, textures and sound effects
ACE-Step
ACE Studio · Music
0.02 credits a second on Voyager
Open model for quick song sketches
Mirelo SFX 2.0
Mirelo · Sound effects
1 credit a second on Voyager
Sound effects that match your video, or from a description
Qwen3-TTS 1.7B
Alibaba · Text to speech
9 credits per 1,000 characters on Voyager
Fixes a line in the speaker's own voice
Scribe v2
ElevenLabs · Transcribe
from 0.8 credits a minute on Voyager
Transcripts with word timing and who's speaking
SAM Audio
Meta · Separate audio
0.17 credits a second on Voyager
Pulls one sound out of a mix by describing it
Eleven Dubbing
ElevenLabs · Dub
60 credits a minute on Voyager
Translates the speech in your video into another language, in the same voices
Eleven Voice Changer
ElevenLabs · Change voice
0.14 credits a second on Voyager
Turns your recording into another voice, keeping the delivery
Eleven Voice Isolator
ElevenLabs · Separate audio
10 credits a minute on Voyager
Pulls clean dialogue out of noisy recordings
Lyria 3
Google · Music
4 credits a request on Voyager
30-second music clips
Lyria 3 Pro
Google · Music
8 credits a request on Voyager
Songs up to 3 minutes
Fish Audio S2 Pro
Fish Audio · Text to speech
1.5 credits per 1,000 characters on Voyager
Earlier Fish Audio voices
Stable Audio 2.5
Stability AI · Music
20 credits a request on Voyager
Earlier Stable Audio; Stable Audio 3 replaced it
Eleven Sound Effects v2
ElevenLabs · Sound effects
from 12 credits a minute on Voyager
Earlier Eleven Sound Effects; v3 replaced it
Eleven Music
ElevenLabs · Music
from 15 credits a minute on Voyager
The first Eleven Music; Eleven Music v2.5 replaced it
Eleven Multilingual v2
ElevenLabs · Text to speech
from 7.2 credits a minute on Voyager
Steady narration in 29 languages
Eleven Flash v2.5
ElevenLabs · Text to speech
from 3.6 credits a minute on Voyager
Very fast speech
Mirelo SFX 1.6
Mirelo · Sound effects
1 credit a second on Voyager
Earlier Mirelo; Mirelo SFX 2.0 replaced it
Other
Meshy 7.1
Meshy · Text to 3D, Image to 3D
40–60 credits a request on Voyager
Game-ready models and rigged, animated characters
Idol
Sperid Labs · Image to 3D
from 10 credits a request on Voyager
Gaussian splats of an object from one image
Tripo P2
Tripo · Image to 3D
from 110 credits a request on Voyager
Low-poly models from an image
Rodin 2.5
Hyper3D · Text to 3D
40–120 credits a request on Voyager
3D objects from text or images, with a fast mode
Tripo H3.1
Tripo · Text to 3D
from 20 credits a request on Voyager
Game assets with materials and a face budget
TRELLIS 2
Microsoft · Image to 3D
25–35 credits a request on Voyager
Detailed meshes from a single image
Hunyuan3D 3
Tencent · Text to 3D
22–45 credits a request on Voyager
Meshes from an image or a description
Meshy Text to Motion
Meshy · Text to motion
from 20 credits a request on Voyager
Character animation from a description
Meshy 7
Meshy · Text to 3D, Image to 3D
from 40 credits a request on Voyager
Earlier Meshy; Meshy 7.1 replaced it
Meshy 6
Meshy · Text to 3D, Image to 3D
from 40 credits a request on Voyager
Quick 3D drafts before a final model
Every image model page runs the same 12 prompts (prompt set 2026-09-09): text in an image, a product on white, a face and hands, a logo, a busy scene, a named art style, a chart, a wide banner, an infographic, food, a hard composition and an edit of an earlier result. Every video model page runs the same 9 clips (clip set 2026-09-09): a product turntable, a person speaking, a title card, a camera move, a spill, hands at work, a busy scene, a named art style and a clip started from one of the image results. Output is shown as it came back.
















