No filming:An AI avatar or clone yourself

    Catalog report · Versely

    The quality-per-credit frontier

    86 models in the catalog hold a current third-party arena score. Plot score against credits per job and only 12 of them sit on the frontier — the rest cost more, score less, or both. This report draws that frontier for all 5 arenas and shows how each release-year cohort shifted it.

    How this report is built — read this before the tables

    The quality scores are not ours. Every ranked model in the catalog is matched by name to an entry on Artificial Analysis, an independent benchmarking site that runs public human-preference arenas for image, video and speech models, and each row carries that arena's current ELO for the matched entry. The tables below show the exact Artificial Analysis leaderboard name each score was taken from, and each section links the specific arena. The credit prices are ours; the scores are theirs.

    One honest caveat, stated here rather than in a footnote: the catalog stores each model's current arena score only — there is no score history. Every “frontier over time” view on this page is therefore constructed by grouping models by their release date and reading today's scores across those groups. It shows what each generation of models is worth now, not what any leaderboard looked like on a past date — older models' scores keep moving as new arena votes come in.

    Price means one thing throughout: credits per job — the fewest credits one complete generation can cost on Versely, taken from each model's own price matrix. That is the only figure comparable across models that bill per second, per megapixel or flat per call. Scored models that publish only a per-1,000-character rate are listed with that rate labeled as such and kept out of the charts and the frontier. The pool is the published model catalog — one row per model page, so every row here is a model you can actually open and run.

    Reading the frontier

    A model is on the frontier when nothing in its arena scores higher at its price or below. Everything off the frontier is dominated: some other model gives more score for the same credits or the same score for fewer. Frontier rows are highlighted in every table; cohorts with fewer than 3 priced models are shown in the cohort tables but not narrated.

    What the data says

    • Text-to-video: the 2025 cohort peaks at 959 ELO, the 2026 cohort at 1143. Outscoring the 2025 peak now starts at 4 credits per job (Wan 3.0 Text to Video).
    • Image-to-video: the 2025 cohort peaks at 947 ELO, the 2026 cohort at 1024. Outscoring the 2025 peak now starts at 17 credits per job (Happy Horse 1.1 Image to Video).
    • Text-to-image: the 2024 cohort peaks at 871 ELO, the 2026 cohort at 1189. Outscoring the 2024 peak now starts at 1 credits per job (FLUX 3 Image Klein).
    • Image editing: the 2025 cohort peaks at 1119 ELO, the 2026 cohort at 1183. Outscoring the 2025 peak now starts at 4 credits per job (GPT Image 2.5 Flare Edit).

    Text-to-video

    18 scored models · scores from the Artificial Analysis Text to Video arena

    The strongest 2025 release in this pool, VEO 3.1, holds 959 ELO today; a clip starts at 32 credits. The strongest 2026 release, HeyGen Video, holds 1143 ELO; a clip starts at 8.

    The cheapest way to outscore the best 2025 release is Wan 3.0 Text to Video (1131 ELO, released 2026), where a clip starts at 4 credits.

    Released inPriced modelsBest score todayLowest job floor
    20253959 ELO — VEO 3.1 at 32-192 credits2-32 credits — PrunaAI P-Video at 801 ELO
    2026151143 ELO — HeyGen Video at 8-72 credits4-120 credits — Wan 3.0 Text to Video at 1131 ELO
    Frontier — top score at its price or belowOther ranked models
    8009001000110023510203050100200Credits per job (log scale) — fewest credits one complete generation can costArena ELO (Artificial Analysis)Minimax H3 Text to Video (2026) — ELO 1120, 12-78 credits. Scored as "MiniMax H3 (768p)" on Artificial Analysis.Seedance 2.5 (2026) — ELO 1103, 22-320 credits. Scored as "Dreamina Seedance 2.5" on Artificial Analysis.Flux 3 Text to Video (2026) — ELO 1091, 34-136 credits. Scored as "FLUX 3" on Artificial Analysis.Seedance 2.0 (2026) — ELO 1085, 22-1639 credits. Scored as "Dreamina Seedance 2.0" on Artificial Analysis.Grok Imagine Video 1.5 Text to Video (2026) — ELO 1038, 4-150 credits. Scored as "Grok Imagine Video 1.5" on Artificial Analysis.Happy Horse 1.1 Text to Video (2026) — ELO 1034, 17-108 credits. Scored as "HappyHorse-1.1" on Artificial Analysis.Wan 2.7 Text to Video (2026) — ELO 1023, 8-90 credits. Scored as "Wan2.7-260612" on Artificial Analysis.Kling Video V3 Pro Text to Video (2026) — ELO 1000, 34-101 credits. Scored as "Kling 3.0 1080p (Pro)" on Artificial Analysis.Pixverse V6 Text to Video (2026) — ELO 991, 5-29 credits. Scored as "PixVerse V6" on Artificial Analysis.VEO 3.1 (2025) — ELO 959, 32-192 credits. Scored as "Veo 3.1" on Artificial Analysis.LTX 2.5 Text to Video Pro (2026) — ELO 927, 58-136 credits. Scored as "LTX-2.5 Pro" on Artificial Analysis.Runway Gen-4.5 (2025) — ELO 910, 200-400 credits. Scored as "Runway Gen-4.5 (720p)" on Artificial Analysis.Vidu Q3 Video (2026) — ELO 902, 23-67 credits. Scored as "Vidu Q3 Pro" on Artificial Analysis.LTX 2.3 Text to Video Fast (2026) — ELO 848, 20-256 credits. Scored as "LTX-2.3 Fast" on Artificial Analysis.Boreal (2026) — ELO 826, 4-192 credits. Scored as "Boreal" on Artificial Analysis.PrunaAI P-Video (2025) — ELO 801, 2-32 credits. Scored as "P-Video" on Artificial Analysis.Wan 3.0 Text to Video (2026) — ELO 1131, 4-120 credits. Scored as "Wan 3.0" on Artificial Analysis.HeyGen Video (2026) — ELO 1143, 8-72 credits. Scored as "HeyGen Video 1" on Artificial Analysis.PrunaAI P-Video ’25Wan 3.0 Text to Video ’26HeyGen Video ’26

    Every scored text-to-video model, by arena score

    #ModelReleasedCredits per jobArena ELOScored as (Artificial Analysis)
    1HeyGen VideoFrontierSeptember 30, 20268-72 credits1143HeyGen Video 1
    2Wan 3.0 Text to VideoFrontierAugust 24, 20264-120 credits1131Wan 3.0
    3Minimax H3 Text to VideoAugust 5, 202612-78 credits1120MiniMax H3 (768p)
    4Seedance 2.5August 1, 202622-320 credits1103Dreamina Seedance 2.5
    5Flux 3 Text to VideoAugust 5, 202634-136 credits1091FLUX 3
    6Seedance 2.0February 12, 202622-1639 credits1085Dreamina Seedance 2.0
    7Grok Imagine Video 1.5 Text to VideoMay 1, 20264-150 credits1038Grok Imagine Video 1.5
    8Happy Horse 1.1 Text to VideoJune 23, 202617-108 credits1034HappyHorse-1.1
    9Wan 2.7 Text to VideoApril 6, 20268-90 credits1023Wan2.7-260612
    10Kling Video V3 Pro Text to VideoFebruary 5, 202634-101 credits1000Kling 3.0 1080p (Pro)
    11Pixverse V6 Text to VideoMarch 30, 20265-29 credits991PixVerse V6
    12VEO 3.1October 15, 202532-192 credits959Veo 3.1
    13LTX 2.5 Text to Video ProAugust 24, 202658-136 credits927LTX-2.5 Pro
    14Runway Gen-4.5December 1, 2025200-400 credits910Runway Gen-4.5 (720p)
    15Vidu Q3 VideoJanuary 30, 202623-67 credits902Vidu Q3 Pro
    16LTX 2.3 Text to Video FastMarch 5, 202620-256 credits848LTX-2.3 Fast
    17BorealSeptember 15, 20264-192 credits826Boreal
    18PrunaAI P-VideoFrontierJuly 29, 20252-32 credits801P-Video

    # is the model's position within Versely's published catalog for this arena, not its position on the full Artificial Analysis leaderboard.

    Image-to-video

    8 scored models · scores from the Artificial Analysis Image to Video arena

    The strongest 2025 release in this pool, VEO First Last Frame, holds 947 ELO today; a clip starts at 32 credits. The strongest 2026 release, Happy Horse 1.1 Image to Video, holds 1024 ELO; a clip starts at 17.

    The cheapest way to outscore the best 2025 release is Happy Horse 1.1 Image to Video (1024 ELO, released 2026), where a clip starts at 17 credits.

    Released inPriced modelsBest score todayLowest job floor
    20254947 ELO — VEO First Last Frame at 32-128 credits12-80 credits — Pika 2.5 Image to Video at 847 ELO
    202641024 ELO — Happy Horse 1.1 Image to Video at 17-108 credits17-108 credits — Happy Horse 1.1 Image to Video at 1024 ELO
    Frontier — top score at its price or belowOther ranked models
    800850900950100010203050100200Credits per job (log scale) — fewest credits one complete generation can costArena ELO (Artificial Analysis)Kling O3 Pro Image to Video (2026) — ELO 1015, 56-168 credits. Scored as "Kling 3.0 Omni 1080p (Pro)" on Artificial Analysis.VEO First Last Frame (2025) — ELO 947, 32-128 credits. Scored as "Veo 3.1" on Artificial Analysis.Vidu Q3 Image to Video (2026) — ELO 906, 23-67 credits. Scored as "Vidu Q3 Pro" on Artificial Analysis.Runway Gen-4.5 (2025) — ELO 896, 200-400 credits. Scored as "Runway Gen-4.5 (720p)" on Artificial Analysis.Kling O1 Image to Video (2025) — ELO 865, 45-90 credits. Scored as "Kling O1 Pro (January)" on Artificial Analysis.LTX 2.3 Image to Video Pro (2026) — ELO 812, 29-192 credits. Scored as "LTX-2.3 Pro" on Artificial Analysis.Pika 2.5 Image to Video (2025) — ELO 847, 12-80 credits. Scored as "Pika 2.5" on Artificial Analysis.Happy Horse 1.1 Image to Video (2026) — ELO 1024, 17-108 credits. Scored as "HappyHorse-1.1" on Artificial Analysis.Pika 2.5 Image to Video ’25Happy Horse 1.1 Image to Video ’26

    Every scored image-to-video model, by arena score

    #ModelReleasedCredits per jobArena ELOScored as (Artificial Analysis)
    1Happy Horse 1.1 Image to VideoFrontierJune 23, 202617-108 credits1024HappyHorse-1.1
    2Kling O3 Pro Image to VideoFebruary 5, 202656-168 credits1015Kling 3.0 Omni 1080p (Pro)
    3VEO First Last FrameOctober 15, 202532-128 credits947Veo 3.1
    4Vidu Q3 Image to VideoJanuary 30, 202623-67 credits906Vidu Q3 Pro
    5Runway Gen-4.5December 1, 2025200-400 credits896Runway Gen-4.5 (720p)
    6Kling O1 Image to VideoDecember 1, 202545-90 credits865Kling O1 Pro (January)
    7Pika 2.5 Image to VideoFrontierNovember 1, 202512-80 credits847Pika 2.5
    8LTX 2.3 Image to Video ProMarch 5, 202629-192 credits812LTX-2.3 Pro

    # is the model's position within Versely's published catalog for this arena, not its position on the full Artificial Analysis leaderboard.

    Text-to-image

    34 scored models · scores from the Artificial Analysis Text to Image arena

    The strongest 2024 release in this pool, Flux 1.1 Pro, holds 871 ELO today; an image starts at 4 credits. The strongest 2026 release, GPT Image 2 Text to Image, holds 1189 ELO; an image starts at 9.

    The cheapest way to outscore the best 2024 release is FLUX 3 Image Klein (1043 ELO, released 2026), where an image starts at 1 credits.

    Released inPriced modelsBest score todayLowest job floor
    20243871 ELO — Flux 1.1 Pro at 4 credits1 credit — Luma Photon Flash at 844 ELO
    2025121123 ELO — GPT Image 1.5 at 2 credits1 credit — Wan 2.6 Text to Image at 1015 ELO
    2026191189 ELO — GPT Image 2 Text to Image at 9-17 credits1 credit — FLUX 3 Image Klein at 1043 ELO
    Frontier — top score at its price or belowOther ranked models
    800900100011001200123510Credits per job (log scale) — fewest credits one complete generation can costArena ELO (Artificial Analysis)Nano Banana 2 (2026) — ELO 1140, 3-6 credits. Scored as "Nano Banana 2 (Gemini 3.1 Flash Image)" on Artificial Analysis.GPT Image 1.5 (2025) — ELO 1123, 2 credits. Scored as "GPT Image 1.5 (high)" on Artificial Analysis.FLUX 3 Image (2026) — ELO 1119, 4 credits. Scored as "FLUX 3 Image" on Artificial Analysis.Seedream 5.0 Pro (2026) — ELO 1101, 6 credits. Scored as "Seedream 5.0 Pro" on Artificial Analysis.Qwen Image 3 Text to Image (2026) — ELO 1072, 3 credits. Scored as "Qwen-Image-3.0" on Artificial Analysis.Grok Imagine Image Quality (2025) — ELO 1049, 4 credits. Scored as "grok-imagine-image-quality" on Artificial Analysis.Fibo 2.0 (2026) — ELO 1040, 4 credits. Scored as "Fibo 2.0" on Artificial Analysis.Seedream 4.5 (2025) — ELO 1027, 4 credits. Scored as "Seedream 4.5" on Artificial Analysis.Flux 2 Flex (2025) — ELO 1026, 4 credits. Scored as "FLUX.2 [flex]" on Artificial Analysis.Luma UNI 1 Max (2026) — ELO 1024, 9 credits. Scored as "Luma UNI 1 Max" on Artificial Analysis.Grok Imagine Image (2025) — ELO 1022, 2 credits. Scored as "grok-imagine-image" on Artificial Analysis.Flux 2 Max (2025) — ELO 1021, 6 credits. Scored as "FLUX.2 [max]" on Artificial Analysis.HiDream O1 Image (2026) — ELO 1017, 1 credit. Scored as "HiDream-O1-Image-1.5" on Artificial Analysis.Wan 2.6 Text to Image (2025) — ELO 1015, 1 credit. Scored as "Wan2.6 Text to Image" on Artificial Analysis.Krea 2 Medium (2026) — ELO 1012, 3 credits. Scored as "Krea 2 Medium" on Artificial Analysis.Ideogram V4 (2026) — ELO 1002, 5 credits. Scored as "Ideogram 4.0" on Artificial Analysis.Cosmos 3 Super (2026) — ELO 993, 4 credits. Scored as "Cosmos3-Super-Text2Image (agentic)" on Artificial Analysis.Flux 2 Flash (2026) — ELO 988, 1 credit. Scored as "FLUX.2 [dev] Flash" on Artificial Analysis.Nano Banana (2025) — ELO 985, 2 credits. Scored as "Nano Banana (Gemini 2.5 Flash Image)" on Artificial Analysis.Qwen Image (2025) — ELO 953, 1 credit. Scored as "Qwen Image Plus 2601" on Artificial Analysis.Z Image Turbo (2025) — ELO 936, 1 credit. Scored as "Z-Image Turbo" on Artificial Analysis.Flux 2 Klein 9B Base (2026) — ELO 930, 1 credit. Scored as "FLUX.2 [klein] 9B" on Artificial Analysis.Kling Image 3.0 (2026) — ELO 919, 3 credits. Scored as "Kling Image 3.0 Omni" on Artificial Analysis.ERNIE Image Turbo (2026) — ELO 915, 1 credit. Scored as "ERNIE Image Turbo" on Artificial Analysis.Qwen Z Image (2025) — ELO 891, 2 credits. Scored as "Z-Image Base" on Artificial Analysis.Leonardo Lucid Origin (2025) — ELO 878, 4 credits. Scored as "Lucid Origin Ultra" on Artificial Analysis.Flux 1.1 Pro (2024) — ELO 871, 4 credits. Scored as "FLUX1.1 [pro]" on Artificial Analysis.Luma Photon Flash (2024) — ELO 844, 1 credit. Scored as "Luma Photon" on Artificial Analysis.HiDream O1 Image Dev (2026) — ELO 809, 1 credit. Scored as "HiDream-O1-Image-Dev" on Artificial Analysis.Flux Schnell (2024) — ELO 740, 1 credit. Scored as "FLUX.1 [schnell]" on Artificial Analysis.FLUX 3 Image Klein (2026) — ELO 1043, 1 credit. Scored as "FLUX 3 Image Klein" on Artificial Analysis.Grok Imagine Image 2.0 (2026) — ELO 1168, 2-3 credits. Scored as "Grok Imagine Image 2.0" on Artificial Analysis.Nano Banana 2.1 (2026) — ELO 1176, 4-7 credits. Scored as "Nano Banana 2.1" on Artificial Analysis.GPT Image 2 Text to Image (2026) — ELO 1189, 9-17 credits. Scored as "GPT Image 2 (high)" on Artificial Analysis.FLUX 3 Image Klein ’26Grok Imagine Image 2.0 ’26Nano Banana 2.1 ’26GPT Image 2 Text to Image ’26

    Every scored text-to-image model, by arena score

    #ModelReleasedCredits per jobArena ELOScored as (Artificial Analysis)
    1GPT Image 2 Text to ImageFrontierApril 21, 20269-17 credits1189GPT Image 2 (high)
    2Nano Banana 2.1FrontierOctober 8, 20264-7 credits1176Nano Banana 2.1
    3Grok Imagine Image 2.0FrontierAugust 24, 20262-3 credits1168Grok Imagine Image 2.0
    4Nano Banana 2February 26, 20263-6 credits1140Nano Banana 2 (Gemini 3.1 Flash Image)
    5GPT Image 1.5December 16, 20252 credits1123GPT Image 1.5 (high)
    6FLUX 3 ImageOctober 1, 20264 credits1119FLUX 3 Image
    7Seedream 5.0 ProAugust 5, 20266 credits1101Seedream 5.0 Pro
    8Qwen Image 3 Text to ImageAugust 1, 20263 credits1072Qwen-Image-3.0
    9Grok Imagine Image QualityJuly 28, 20254 credits1049grok-imagine-image-quality
    10FLUX 3 Image KleinFrontierOctober 15, 20261 credit1043FLUX 3 Image Klein
    11Fibo 2.0October 19, 20264 credits1040Fibo 2.0
    12Seedream 4.5December 4, 20254 credits1027Seedream 4.5
    13Flux 2 FlexNovember 25, 20254 credits1026FLUX.2 [flex]
    14Luma UNI 1 MaxMarch 5, 20269 credits1024Luma UNI 1 Max
    15Grok Imagine ImageJuly 28, 20252 credits1022grok-imagine-image
    16Flux 2 MaxDecember 16, 20256 credits1021FLUX.2 [max]
    17HiDream O1 ImageMay 8, 20261 credit1017HiDream-O1-Image-1.5
    18Wan 2.6 Text to ImageDecember 16, 20251 credit1015Wan2.6 Text to Image
    19Krea 2 MediumMay 12, 20263 credits1012Krea 2 Medium
    20Ideogram V4June 3, 20265 credits1002Ideogram 4.0
    21Cosmos 3 SuperJune 1, 20264 credits993Cosmos3-Super-Text2Image (agentic)
    22Flux 2 FlashJanuary 15, 20261 credit988FLUX.2 [dev] Flash
    23Nano BananaAugust 26, 20252 credits985Nano Banana (Gemini 2.5 Flash Image)
    24Qwen ImageAugust 4, 20251 credit953Qwen Image Plus 2601
    25Z Image TurboNovember 27, 20251 credit936Z-Image Turbo
    26Flux 2 Klein 9B BaseJanuary 15, 20261 credit930FLUX.2 [klein] 9B
    27Kling Image 3.0February 5, 20263 credits919Kling Image 3.0 Omni
    28ERNIE Image TurboApril 15, 20261 credit915ERNIE Image Turbo
    29Qwen Z ImageNovember 27, 20252 credits891Z-Image Base
    30Leonardo Lucid OriginAugust 5, 20254 credits878Lucid Origin Ultra
    31Flux 1.1 ProOctober 2, 20244 credits871FLUX1.1 [pro]
    32Luma Photon FlashNovember 25, 20241 credit844Luma Photon
    33HiDream O1 Image DevMay 8, 20261 credit809HiDream-O1-Image-Dev
    34Flux SchnellAugust 1, 20241 credit740FLUX.1 [schnell]

    # is the model's position within Versely's published catalog for this arena, not its position on the full Artificial Analysis leaderboard.

    Image editing

    18 scored models · scores from the Artificial Analysis Image Editing arena

    The strongest 2025 release in this pool, GPT Image 1.5, holds 1119 ELO today; an edit starts at 2 credits. The strongest 2026 release, GPT Image 2.5 Flare Edit, holds 1183 ELO; an edit starts at 4.

    The cheapest way to outscore the best 2025 release is GPT Image 2.5 Flare Edit (1183 ELO, released 2026), where an edit starts at 4 credits.

    Released inPriced modelsBest score todayLowest job floor
    202581119 ELO — GPT Image 1.5 at 2 credits1 credit — Qwen Image Edit 2511 at 993 ELO
    2026101183 ELO — GPT Image 2.5 Flare Edit at 4-7 credits1 credit — Pruna Image Edit at 985 ELO
    Frontier — top score at its price or belowOther ranked models
    900100011001200123510Credits per job (log scale) — fewest credits one complete generation can costArena ELO (Artificial Analysis)Nano Banana 2.1 (2026) — ELO 1151, 4-7 credits. Scored as "Nano Banana 2.1" on Artificial Analysis.Mai Image 2.5 Edit (2026) — ELO 1127, 4 credits. Scored as "MAI-Image-2.5" on Artificial Analysis.FLUX 3 Image Edit (2026) — ELO 1123, 4 credits. Scored as "FLUX 3 Image" on Artificial Analysis.HunyuanImage 3.0 Instruct Edit (2026) — ELO 1064, 8 credits. Scored as "HunyuanImage 3.0 Instruct" on Artificial Analysis.Wan 2.7 Pro Edit (2026) — ELO 1051, 6 credits. Scored as "Wan 2.7 Pro" on Artificial Analysis.GPT Image 1 Edit (2025) — ELO 998, 2 credits. Scored as "GPT Image 1 (high)" on Artificial Analysis.Pruna Image Edit (2026) — ELO 985, 1 credit. Scored as "P-Image-Edit" on Artificial Analysis.Qwen Image Edit (2025) — ELO 984, 1 credit. Scored as "Qwen Image Edit Max 2601" on Artificial Analysis.Qwen Image 2 Edit (2026) — ELO 968, 3 credits. Scored as "Qwen Image 2.0 (2026-03-03)" on Artificial Analysis.HiDream O1 Image Edit (2026) — ELO 955, 1 credit. Scored as "HiDream-O1-Image" on Artificial Analysis.Kling Image O1 (2025) — ELO 944, 3 credits. Scored as "Kling Image O1" on Artificial Analysis.Flux 2 Klein 4B Base Edit (2026) — ELO 941, 1 credit. Scored as "FLUX.2 [klein] 4B" on Artificial Analysis.Flux Kontext (2025) — ELO 915, 1 credit. Scored as "FLUX.1 Kontext [pro]" on Artificial Analysis.Seedream Edit (2025) — ELO 901, 1 credit. Scored as "SeedEdit 3.0" on Artificial Analysis.LongCat Edit (2025) — ELO 897, 12 credits. Scored as "LongCat Image" on Artificial Analysis.Qwen Image Edit 2511 (2025) — ELO 993, 1 credit. Scored as "Qwen Image Edit Plus 2511" on Artificial Analysis.GPT Image 1.5 (2025) — ELO 1119, 2 credits. Scored as "GPT Image 1.5 (high)" on Artificial Analysis.GPT Image 2.5 Flare Edit (2026) — ELO 1183, 4-7 credits. Scored as "GPT Image 2.5 Flare (max)" on Artificial Analysis.Qwen Image Edit 2511 ’25GPT Image 1.5 ’25GPT Image 2.5 Flare Edit ’26

    Every scored image editing model, by arena score

    #ModelReleasedCredits per jobArena ELOScored as (Artificial Analysis)
    1GPT Image 2.5 Flare EditFrontierSeptember 8, 20264-7 credits1183GPT Image 2.5 Flare (max)
    2Nano Banana 2.1October 8, 20264-7 credits1151Nano Banana 2.1
    3Mai Image 2.5 EditJune 2, 20264 credits1127MAI-Image-2.5
    4FLUX 3 Image EditOctober 1, 20264 credits1123FLUX 3 Image
    5GPT Image 1.5FrontierDecember 16, 20252 credits1119GPT Image 1.5 (high)
    6HunyuanImage 3.0 Instruct EditJanuary 26, 20268 credits1064HunyuanImage 3.0 Instruct
    7Wan 2.7 Pro EditApril 6, 20266 credits1051Wan 2.7 Pro
    8GPT Image 1 EditApril 23, 20252 credits998GPT Image 1 (high)
    9Qwen Image Edit 2511FrontierDecember 23, 20251 credit993Qwen Image Edit Plus 2511
    10Pruna Image EditJanuary 1, 20261 credit985P-Image-Edit
    11Qwen Image EditAugust 19, 20251 credit984Qwen Image Edit Max 2601
    12Qwen Image 2 EditFebruary 10, 20263 credits968Qwen Image 2.0 (2026-03-03)
    13HiDream O1 Image EditMay 8, 20261 credit955HiDream-O1-Image
    14Kling Image O1December 1, 20253 credits944Kling Image O1
    15Flux 2 Klein 4B Base EditJanuary 15, 20261 credit941FLUX.2 [klein] 4B
    16Flux KontextMay 29, 20251 credit915FLUX.1 Kontext [pro]
    17Seedream EditSeptember 9, 20251 credit901SeedEdit 3.0
    18LongCat EditDecember 5, 202512 credits897LongCat Image

    # is the model's position within Versely's published catalog for this arena, not its position on the full Artificial Analysis leaderboard.

    Text-to-speech

    11 scored models · scores from the Artificial Analysis Text to Speech arena

    This arena's pool is too small to cut into release-year cohorts honestly — fewer than two cohorts reach 3 priced models — so it gets the full ranking only, no trend claims.

    Every scored text-to-speech model, by arena score

    #ModelReleasedCredits per jobArena ELOScored as (Artificial Analysis)
    1Eleven v4September 28, 20267 credits (headline rate)1334Eleven v4
    2Cartesia Sonic 3.6August 27, 20264 credits (headline rate)1293Sonic 3.6
    3Gemini 3.8 Flash TTSSeptember 23, 20262 credits (headline rate)1282Gemini 3.8 Flash TTS
    4Inworld TTS 2May 5, 20262 credits (headline rate)1266Realtime TTS-2
    5Inworld TTS 2 FlashSeptember 2, 20262 credits (headline rate)1215Realtime TTS-2 Flash
    6Gemini 3.1 Flash TTSApril 15, 202612 credits (headline rate)1213Gemini 3.1 Flash TTS
    7Cartesia Sonic 3.5June 16, 20264 credits (headline rate)1193Sonic 3.5
    8MiniMax SpeechApril 2, 20252 credits (headline rate)1173Speech 2.8 HD
    9Grok TTSMarch 16, 20264 credits (headline rate)1157SpaceXAI TTS
    10Chatterbox TTSMay 1, 20252 credits (headline rate)1108Chatterbox HD
    11ElevenLabs Speech TurboJuly 19, 20244 credits (headline rate)1092Turbo v2.5

    # is the model's position within Versely's published catalog for this arena, not its position on the full Artificial Analysis leaderboard. 11 of the 11 rows publish no complete-job minimum — their credit figure is the headline rate, labeled, and they are excluded from the chart and the frontier.

    Turn the frontier into a pick

    This page tells you where quality stops being worth extra credits — it does not know your aspect ratio, clip length or style. The /best rankings cut the same catalog by use case (platform, resolution, budget, speed), and every model in every table above links to its page in the model catalog with full pricing, settings and prompt guidance. New releases land in what's new first — when the frontier moves, it moves there.

    Frequently asked questions

    Where do the quality scores on this page come from?+

    From Artificial Analysis (artificialanalysis.ai), an independent AI benchmarking site that runs public human-preference arenas for text-to-image, image editing, text-to-video, image-to-video and text-to-speech models. Versely syncs those arena ELO scores into its catalog and matches them to catalog models by name — the 'scored as' column in each table shows the exact Artificial Analysis leaderboard entry a score was taken from. The scores are theirs; the credit prices are ours.

    What does 'credits per job' mean?+

    The fewest credits one complete generation can cost on Versely — the price matrix's own minimum for a full job, not a per-second or per-character rate read out of context. It is the only credit figure that is comparable across models that bill per second, per megapixel, or flat per call. A handful of scored audio models publish only a per-1,000-character rate with no complete-job minimum; those rows are labeled 'headline rate' and are excluded from the charts and the frontier rather than passed off as job prices.

    Is the 'frontier over time' a history of past leaderboards?+

    No, and the page says so where the numbers are used: the catalog stores each model's current arena score only. The cohort views group models by their release year and read today's scores across those groups. That shows what each generation of models is worth now — it does not show what the leaderboard looked like on any past date, because scores of older models keep moving as new arena votes come in.

    Does a higher arena ELO mean that model is better for my job?+

    Not automatically. Arena ELO measures which model's output people preferred across broad prompt sets — it says nothing about your specific style, aspect ratio, clip length or budget. Use this report to find the price band where quality stops improving for you, then check the use-case rankings under /best and the individual model pages under /models for the constraints that actually decide the pick.

    Run the frontier models inside Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync, in your browser or on your phone.

    One account for the web and iPhone.