# MiniMax H3 Max > Make a 5–15 second MiniMax H3 Max clip with sound. A 5-second shot renders in under 3 seconds. Write a prompt or upload a still; new accounts get 10 credits. MiniMax H3 Max is an independent product and is not affiliated with, endorsed by, or sponsored by MiniMax. Related model names are trademarks of their respective owners, used here for identification only. We provide access to third-party AI models through our own interface. Models are accessed through licensed APIs. Uploaded photos are used only to make the result you asked for, show it in your history and run safety checks. They are never used to train our models or to build face templates, and uploads and results are deleted about 30 days after they are made (kept longer while a subscription is active). Details: [Privacy Policy](https://minimaxh3max.com/legal/privacy). ## Primary Tools - [MiniMax H3 Max](https://minimaxh3max.com/): Make a 5–15 second MiniMax H3 Max clip with sound. A 5-second shot renders in under 3 seconds. Write a prompt or upload a still; new accounts get 10 credits. ## Image - [MiniMax H3 Image](https://minimaxh3max.com/minimax-h3-image): Make pictures with MiniMax H3 Image online. Write a short prompt or upload up to 16 reference images, get 2K or 4K results. New accounts get 10 free credits. ## Guides - [MiniMax H3 Prompt Guide](https://minimaxh3max.com/minimax-h3-prompt-guide): A MiniMax H3 prompting guide: pick T2VA, I2VA, FL2VA, L2VA or Ref2VA from the files you have, fill each field, and copy prompts to paste into MiniMax H3 Max. ## Pricing and Plans - [Pricing](https://minimaxh3max.com/pricing): Compare MiniMax H3 Max subscription plans and one-time credit packs, with usage estimates for every model. - [Pricing details](https://minimaxh3max.com/pricing.md): Plans, credit rules, free credits and the credits each model and option costs. ## AI Docs - [Model details](https://minimaxh3max.com/models.md): Every model on this site with its modes, reference inputs, aspect ratios, resolutions or durations, and credits. - [Full guide](https://minimaxh3max.com/llms-full.txt): This file plus the pricing and model details in one document. --- # MiniMax H3 Max pricing and credits Canonical page: https://minimaxh3max.com/pricing Generated from the live plan and model configuration of minimaxh3max.com. Prices are in US dollars unless a currency is shown. ## Free credits - New accounts get 10 free credits, enough for a run of MiniMax H3 Image (2 credits). - Free-tier images carry a watermark; paid plans remove it. - Higher resolutions need paid credits. - More than one output per run needs paid credits. ## Subscriptions | Plan | Billing | Price | Credits | | --- | --- | --- | --- | | Basic | Monthly | $19.90 / month | 1,000 credits a month (incl. 100 bonus credits) | | Basic | Yearly | $178.80 / year (regular $238.80) | 12,000 credits a year (incl. 1,200 bonus credits), 1,000 added each month | | Standard | Monthly | $39.90 / month | 2,500 credits a month (incl. 500 bonus credits) | | Standard | Yearly | $358.80 / year (regular $478.80) | 30,000 credits a year (incl. 6,000 bonus credits), 2,500 added each month | | Pro | Monthly | $99.90 / month | 7,500 credits a month (incl. 2,500 bonus credits) | | Pro | Yearly | $838.80 / year (regular $1,198.80) | 78,000 credits a year (incl. 30,000 bonus credits), 6,500 added each month | ## Credit packs | Pack | Price | Credits | | --- | --- | --- | | Starter Pack | $14.90 | 600 credits | | Plus Pack | $39.90 | 2,000 credits | | Pro Pack | $59.90 | 4,000 credits | | Max Pack | $99.90 | 7,000 credits | ## Plan features - All paid plans: Commercial-use license under Terms - Basic: Premium image and video models on this site; Image and video editing tools; Standard support - Standard: Premium image and video models on this site; Image and video editing tools; Faster generation speed; Priority support - Pro: Premium image and video models on this site; Image and video editing tools; Faster generation speed; Priority support - Starter Pack: One-time Premium-capable credits for models and tools; Use after subscription credits run out, or without a subscription; Failed generations automatically refund credits; 30-day result storage - Plus Pack: One-time Premium-capable credits for models and tools; Use after subscription credits run out, or without a subscription; Failed generations automatically refund credits; 30-day result storage - Pro Pack: Bulk Premium-capable credits for models and tools; Use after subscription credits run out, or without a subscription; Failed generations automatically refund credits; 30-day result storage - Max Pack: Largest one-time Premium-capable credit top-up; Use after subscription credits run out, or without a subscription; Failed generations automatically refund credits; 30-day result storage ## Offers - Yearly billing, compared with paying monthly for 12 months: - Basic: $178.80 a year (about $14.90 a month) instead of $19.90 a month, 25% less. - Standard: $358.80 a year (about $29.90 a month) instead of $39.90 a month, 25% less. - Pro: $838.80 a year (about $69.90 a month) instead of $99.90 a month, 30% less. 78,000 credits a year vs 90,000 on monthly; $10.75 vs $13.32 per 1,000 credits. ## Credit rules - Subscription credits are replaced by the new allowance at each renewal; unused subscription credits do not carry over. - Yearly plans are billed once a year; their credits are added in 12 monthly instalments. - Credit pack credits never expire. - Credits are spent in this order: subscription credits first, then free credits, then credit pack credits. - A run that fails gets its credits back automatically. - Refunds of unused credits can be requested within 7 days of purchase. ## Payment - Card payments. Alipay and WeChat Pay are also available for credit packs. ## Usage rights - Under the Terms, and to the extent the law and the model providers allow, what you generate on a paid plan or with purchased credits is yours to use, including commercially (ads, client work, products). - Output made only with free credits is for personal, non-commercial use. Full terms: https://minimaxh3max.com/legal/terms ## Credits per generation | Model | Modes | Option | Credits | | --- | --- | --- | --- | | MiniMax H3 Max | Text to video, Image to video, Reference to video | 480P | 10 credits per second | | MiniMax H3 Max | Text to video, Image to video, Reference to video | 768P | 20 credits per second | | MiniMax H3 Max | Text to video, Image to video, Reference to video | 1080P | 35 credits per second | | MiniMax H3 Max | Video to video | 480P | 20 credits per second | | MiniMax H3 Max | Video to video | 768P | 40 credits per second | | MiniMax H3 Max | Video to video | 1080P | 70 credits per second | | MiniMax H3 Max | Video to video | 2K | 140 credits per second | | MiniMax H3 | Text to video, Image to video | 768P | 15 credits per second | | MiniMax H3 | Text to video, Image to video | 2K | 30 credits per second | | MiniMax H3 Image | Text to image | 1K | 2 credits per image | | MiniMax H3 Image | Text to image | 2K | 2 credits per image | | MiniMax H3 Image | Text to image | 4K | 5 credits per image | | MiniMax H3 Image | Image to image | 1K | 2 credits per image | | MiniMax H3 Image | Image to image | 2K | 2 credits per image | | MiniMax H3 Image | Image to image | 4K | 5 credits per image | | MiniMax H3 Image | Image to image | Any | 1 credit per input image | | GPT Image 2 | Text to image, Image to image | 1K | 6 credits per image | | GPT Image 2 | Text to image, Image to image | 2K | 10 credits per image | | GPT Image 2 | Text to image, Image to image | 4K | 20 credits per image | | Nano Banana Pro | Text to image, Image to image | 1K | 20 credits per image | | Nano Banana Pro | Text to image, Image to image | 2K | 20 credits per image | | Nano Banana Pro | Text to image, Image to image | 4K | 25 credits per image | | Nano Banana 2 | Text to image, Image to image | 1K | 8 credits per image | | Nano Banana 2 | Text to image, Image to image | 2K | 15 credits per image | | Nano Banana 2 | Text to image, Image to image | 4K | 20 credits per image | | Nano Banana 2 Lite | Text to image, Image to image | Any | 4 credits per image | | Nano Banana | Text to image, Image to image | Any | 4 credits per image | | Veo 3.1 Fast | Text to video, Image to video, Video to video | 720p | 60 credits per clip | | Veo 3.1 Fast | Text to video, Image to video, Video to video | 1080p | 65 credits per clip | | Veo 3.1 Fast | Text to video, Image to video, Video to video | 4k | 180 credits per clip | | Veo 3.1 | Text to video | 720p | 250 credits per clip | | Veo 3.1 | Text to video | 1080p | 255 credits per clip | | Veo 3.1 | Text to video | 4k | 380 credits per clip | | Veo 3.1 | Image to video | 720p | 250 credits per clip | | Veo 3.1 | Image to video | 1080p | 255 credits per clip | | Veo 3.1 | Image to video | 4k | 370 credits per clip | | Veo 3.1 Lite | Text to video, Image to video | 720p | 30 credits per clip | | Veo 3.1 Lite | Text to video, Image to video | 1080p | 35 credits per clip | | Veo 3.1 Lite | Text to video, Image to video | 4k | 150 credits per clip | | Seedance 2 | Text to video, Image to video | 480p | 20 credits per second | | Seedance 2 | Text to video, Image to video | 720p | 45 credits per second | | Seedance 2 | Text to video, Image to video | 1080p | 105 credits per second | | Seedance 2 | Text to video, Image to video | 4k | 210 credits per second | | Seedance 2 | Video to video | 480p, with reference_video_urls | 15 credits per second | | Seedance 2 | Video to video | 480p, without reference_video_urls | 20 credits per second | | Seedance 2 | Video to video | 720p, with reference_video_urls | 25 credits per second | | Seedance 2 | Video to video | 720p, without reference_video_urls | 40 credits per second | | Seedance 2 | Video to video | 1080p, with reference_video_urls | 65 credits per second | | Seedance 2 | Video to video | 1080p, without reference_video_urls | 95 credits per second | | Seedance 2 | Video to video | 4k, with reference_video_urls | 130 credits per second | | Seedance 2 | Video to video | 4k, without reference_video_urls | 190 credits per second | | Seedance 2 Fast | Text to video, Image to video | 480p | 15 credits per second | | Seedance 2 Fast | Text to video, Image to video | 720p | 25 credits per second | | Seedance 2 Fast | Video to video | 480p, with reference_video_urls | 7 credits per second | | Seedance 2 Fast | Video to video | 480p, without reference_video_urls | 15 credits per second | | Seedance 2 Fast | Video to video | 720p, with reference_video_urls | 15 credits per second | | Seedance 2 Fast | Video to video | 720p, without reference_video_urls | 25 credits per second | | Seedance 2 Mini | Text to video, Image to video | 480p | 4 credits per second | | Seedance 2 Mini | Text to video, Image to video | 720p | 9 credits per second | | Seedance 2 Mini | Video to video | 480p, with reference_video_urls | 3 credits per second | | Seedance 2 Mini | Video to video | 480p, without reference_video_urls | 4 credits per second | | Seedance 2 Mini | Video to video | 720p, with reference_video_urls | 5 credits per second | | Seedance 2 Mini | Video to video | 720p, without reference_video_urls | 8 credits per second | | Seedream 5.0 Flash | Text to image, Image to image | 1K | 3 credits per image | | Seedream 5.0 Flash | Text to image, Image to image | 2K | 3 credits per image | ## Cost in dollars At the lowest price per credit on sale, $0.0108 per credit (Pro, yearly), the cheapest run of each model costs: | Model | Cheapest run | Credits | From | | --- | --- | --- | --- | | MiniMax H3 Max | 5-second clip (480P) | 50 credits | $0.54 | | MiniMax H3 | 5-second clip (768P) | 75 credits | $0.81 | | MiniMax H3 Image | 1 image (1K) | 2 credits | $0.02 | | GPT Image 2 | 1 image (1K) | 6 credits | $0.06 | | Nano Banana Pro | 1 image (1K) | 20 credits | $0.22 | | Nano Banana 2 | 1 image (1K) | 8 credits | $0.09 | | Nano Banana 2 Lite | 1 image | 4 credits | $0.04 | | Nano Banana | 1 image | 4 credits | $0.04 | | Veo 3.1 Fast | 1 clip (720p) | 60 credits | $0.65 | | Veo 3.1 | 1 clip (720p) | 250 credits | $2.69 | | Veo 3.1 Lite | 1 clip (720p) | 30 credits | $0.32 | | Seedance 2 | 4-second clip (480p) | 80 credits | $0.86 | | Seedance 2 Fast | 4-second clip (480p) | 60 credits | $0.65 | | Seedance 2 Mini | 4-second clip (480p) | 16 credits | $0.17 | | Seedream 5.0 Flash | 1 image (1K) | 3 credits | $0.03 | The generator shows the exact credits before you start a run. ## Tools | Tool | Credits | | --- | --- | | Background Remover | 1 credit per run | | Image Extender | 2 credits per run | | Image Upscaler | 2 credits (2x) or 4 credits (4x) or 8 credits (8x) per run | | Photo Restore | 6 credits per run | | Motion Control | 20 credits (720p) or 40 credits (1080p) per second of video, minimum 45 credits per run | | Lip-Sync Video | 5 credits (720p) or 10 credits (1080p) per second of video, minimum 15 credits per run | | Video Upscaler | 2 credits (1080p) or 3 credits (2k) or 6 credits (4k) per second of video | --- # MiniMax H3 Max models Canonical page: https://minimaxh3max.com/ Generated from the live model configuration of minimaxh3max.com. Credit prices per option are in pricing.md. ## MiniMax H3 Max (default video model) - Modes: Text to video, Image to video, Reference to video, Video to video - Image to video inputs: first frame (required), last frame (optional) - Reference images: up to 9 - Reference videos: up to 3 - Reference audio: up to 3 - Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive, auto - Resolutions: 480P, 768P, 1080P, 2K - Duration: 5 to 15 seconds - Outputs per run: 1 to 4 - Credits: Text to video, Image to video, Reference to video: 10 per second (480P) to 35 per second (1080P); Video to video: 20 per second (480P) to 140 per second (2K) ## MiniMax H3 - Modes: Text to video, Image to video - Image to video inputs: first frame (required), last frame (optional) - Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 - Resolutions: 768P, 2K - Duration: 5 to 15 seconds - Credits: 15 per second (768P) to 30 per second (2K) ## MiniMax H3 Image (default image model) - Modes: Text to image, Image to image - Reference images: up to 16 - Aspect ratios: 1:1, 4:5, 5:4, 3:4, 4:3, 2:3, 3:2, 9:16, 16:9, 21:9, auto - Resolutions: 1K, 2K, 4K - Outputs per run: 1 to 4 - Credits: Text to image: 2 per image (1K) to 5 per image (4K); Image to image: 1 per input image to 5 per image (4K) ### Our test runs - Text to image, 1 output, 3:2, 1K: 2 credits, result in 21 s (run on 2026-11-16) - Prompt: "A photograph for a travel guide: a narrow side street in an old harbour town just after evening rain, seen from the middle of the street at eye level. On the left, a small bakery with a dark green awning; gold serif letters on its window read "Marlow & Daughters", and a small handwritten card in the window reads "Fresh bread from 7am". On the right, a bicycle repair shop with a hanging metal sign that reads "Pell Street Cycles" and three bicycles leaning against the brick wall. In the middle distance, a corner cafe with a small red neon sign that reads "OPEN". Wet cobblestones reflect the warm shop lights; a few puddles, a parked pale blue scooter, string lights crossing above the street and potted herbs by the doorways. Blue dusk sky, warm yellow window light, fine detail in the brick, wood grain and wet stone. Natural colors, realistic photo, sharp focus from front to back." - Result: A rainy dusk side street with a green-awning bakery, a hanging "Pell Street Cycles" sign, a pale blue scooter and string lights. The large cycle-shop sign is right; the small "Fresh bread from 7am" card and the far "OPEN" neon are garbled, "Marlow & Daughters" is split and hard to read, and four bikes appear instead of three. - Image: https://cdn.minimaxh3max.com/assets/landing/h3image/samples/h3-t2i-street-1k.webp - Text to image, 1 output, 3:2, 2K: 2 credits, result in 26 s (run on 2026-11-16) - Prompt: "A photograph for a travel guide: a narrow side street in an old harbour town just after evening rain, seen from the middle of the street at eye level. On the left, a small bakery with a dark green awning; gold serif letters on its window read "Marlow & Daughters", and a small handwritten card in the window reads "Fresh bread from 7am". On the right, a bicycle repair shop with a hanging metal sign that reads "Pell Street Cycles" and three bicycles leaning against the brick wall. In the middle distance, a corner cafe with a small red neon sign that reads "OPEN". Wet cobblestones reflect the warm shop lights; a few puddles, a parked pale blue scooter, string lights crossing above the street and potted herbs by the doorways. Blue dusk sky, warm yellow window light, fine detail in the brick, wood grain and wet stone. Natural colors, realistic photo, sharp focus from front to back." - Result: The same street, laid out differently: "Marlow & Daughters" and "Pell Street Cycles" are spelled right, but the small "Fresh bread from 7am" card and the far "OPEN" neon are still garbled; two bikes instead of three. - Image: https://cdn.minimaxh3max.com/assets/landing/h3image/samples/h3-t2i-street-2k.webp - Text to image, 1 output, 3:2, 4K: 5 credits, result in 40 s (run on 2026-11-16) - Prompt: "A photograph for a travel guide: a narrow side street in an old harbour town just after evening rain, seen from the middle of the street at eye level. On the left, a small bakery with a dark green awning; gold serif letters on its window read "Marlow & Daughters", and a small handwritten card in the window reads "Fresh bread from 7am". On the right, a bicycle repair shop with a hanging metal sign that reads "Pell Street Cycles" and three bicycles leaning against the brick wall. In the middle distance, a corner cafe with a small red neon sign that reads "OPEN". Wet cobblestones reflect the warm shop lights; a few puddles, a parked pale blue scooter, string lights crossing above the street and potted herbs by the doorways. Blue dusk sky, warm yellow window light, fine detail in the brick, wood grain and wet stone. Natural colors, realistic photo, sharp focus from front to back." - Result: The same street, laid out differently again: every prompted sign is spelled right, including the small "Fresh bread from 7am" card and the far "OPEN" neon. The window name is painted twice, a small extra card has unreadable letters, and two bikes appear instead of three. - Image: https://cdn.minimaxh3max.com/assets/landing/h3image/samples/h3-t2i-street-4k.webp - Text to image, 1 output, 2:3, 2K: 2 credits, result in 26 s (run on 2026-11-16) - Prompt: "A printed gig poster for a small indie concert, portrait. Layout from top to bottom: a big headline across the top third, an illustration in the middle, two lines of details at the bottom. The headline reads "MOTH & MERIDIAN" in heavy condensed cream capitals. Directly under it, smaller cream text reads "with Juniper Coast". The middle illustration is a screen print of a paper lantern floating above a dark lake with pine trees, in three inks only: cream, coral and deep navy, with visible halftone grain. At the bottom, centered on two lines in coral capitals: "FRIDAY 11 DECEMBER · DOORS 8PM" and "THE TIN ROOM, 44 HARBOUR LANE". In the bottom right corner, small cream text reads "Tickets $15". Flat matte paper with slight ink misregistration. No other text on the poster." - Result: A navy screen-print poster with a lantern over a pine lake; all five text lines are spelled right with their punctuation ("MOTH & MERIDIAN", "with Juniper Coast", the date line, the venue line and "Tickets $15"). The headline is a heavy geometric sans rather than condensed, and the print is shown lying on dark stone. - Image: https://cdn.minimaxh3max.com/assets/landing/h3image/samples/h3-t2i-gig-poster.webp ## GPT Image 2 - Modes: Text to image, Image to image - Reference images: up to 16 - Aspect ratios: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21 - Resolutions: 1K, 2K, 4K - Outputs per run: 1 to 4 - Credits: 6 per image (1K) to 20 per image (4K) ### Our test runs - Text to image, 3:4, 1K, 1 output: 6 credits, result in 51 s (run on 2026-11-10) - Prompt: "A candid street portrait of an elderly fisherman in his seventies on a harbour pier at dawn: weathered skin with deep wrinkles, white stubble, a navy wool beanie and a yellow oilskin jacket, light rain. Shot on a 50mm lens at f/1.8, natural colour, no retouching." - Result: Overcast pier with boats behind him, deep wrinkles and a wet beanie; reads as a real photo. No dawn light. - Image: https://cdn.minimaxh3max.com/assets/landing/aipicturegenerator/best/best-portrait-gpt2.webp ## Nano Banana Pro - Modes: Text to image, Image to image - Reference images: up to 8 - Aspect ratios: 1:1, 9:16, 16:9, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9, auto - Resolutions: 1K, 2K, 4K - Outputs per run: 1 to 4 - Credits: 20 per image (1K) to 25 per image (4K) ### Our test runs - Image to image, 4:3, 2K, 1 output, 3 reference images: 20 credits, result in 107 s (run on 2026-11-14) - Prompt: "Combine the three photos into one shop listing photo. Take the speckled mug with the blue wave pattern from the first photo and the yellow ranunculus from the second photo, unwrapped and arranged in a small clear glass jar of water, and place both on the oak kitchen counter from the third photo, the mug in front and slightly to the left. Keep the mug's shape, speckles and hand-painted wave pattern exactly as they are. Add a little steam rising from the mug, and soft shadows that fall the same way as the window light. Clean, bright lifestyle photo, nothing else on the counter." - Result: The mug keeps its shape, speckles and blue wave painting; the ranunculus stand in a glass jar beside it on the oak counter, with faint steam and window shadows that match. The two herb pots from the counter photo stay in the background. Inputs were three phone-style photos made with GPT Image 2.5 Flare at 1K and sent as JPEG copies. 2400 × 1792. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananapro/samples/composite.webp - Image to image, 1:1, 1K, 1 output, 1 reference images: 20 credits, result in 35 s (run on 2026-11-14) - Prompt: "Turn this workshop photo into a clean shop listing photo. Keep the mug exactly as it is: the same shape, the speckled glaze and the hand-painted blue wave pattern. Remove the workbench, tools and clay dust, and place the mug on a seamless light grey background with a soft natural shadow underneath. Even, bright studio lighting, the mug centred and slightly turned so the handle is on the right." - Result: The mug's shape, speckles and wave painting were kept; the workbench and tools are gone and it sits on a light grey background with a soft shadow, handle on the right. 1024 × 1024. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananapro/prompts/edit-product.webp - Image to image, 4:3, 1K, 1 output, 1 reference images: 20 credits, result in 34 s (run on 2026-11-14) - Prompt: "Change this kitchen photo from a sunny morning to a cosy evening. Keep the same camera angle, the oak counter, the window, the tiles and both herb pots exactly where they are. Outside the window the sky is deep blue after sunset. Turn on warm under-cabinet lights so they glow along the tiles, and add a lit candle in a small glass jar on the counter. Warm, soft shadows, no other changes." - Result: Same angle, counter, window and herb pots; the sky is dark blue, under-cabinet lights glow along the tiles and a lit candle in a jar stands by the pots. 1200 × 896. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananapro/prompts/edit-evening.webp - Text to image, 3:4, 2K, 1 output: 20 credits, result in 104 s (run on 2026-11-14) - Prompt: "A two-colour risograph poster for a neighbourhood jazz night, printed in deep blue and warm orange on cream paper, with visible paper grain and slight misregistration. At the top, a big bold headline reads "MIDNIGHT ON MAPLE STREET". In the middle, a stylised illustration of a double bass player in silhouette under a crescent moon, with a row of brick houses behind. Below it, a line reads "Live Jazz · Friday 12 December · 8 PM". At the very bottom in small type: "Free entry · The Blue Door, 41 Maple Street". Clean, balanced layout with generous margins." - Result: Every line of text came out spelled as written: the two-line headline, the date line and the small venue line. Two-colour blue and orange print look with halftone texture, a bass player silhouette and a row of terraced houses under a crescent moon. 1792 × 2400. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananapro/samples/poster.webp ## Nano Banana 2 - Modes: Text to image, Image to image - Reference images: up to 14 - Aspect ratios: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9, auto - Resolutions: 1K, 2K, 4K - Outputs per run: 1 to 4 - Credits: 8 per image (1K) to 20 per image (4K) ### Our test runs - Image to image, 3:4, 1K, 1 output, 1 reference images: 8 credits, result in 38 s (run on 2026-11-22) - Prompt: "Translate every word on this recipe card into Spanish. Keep the same card, layout, font style, pancakes, marble counter and light. Only the words change." - Result: Title, intro line, ingredients and steps all turned into Spanish; card, pancakes, fork and marble kept. The step text sits a little tighter than the original. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/nb2-edit-translate.webp - Image to image, 1:1, 1K, 1 output, 1 reference images: 8 credits, result in 22 s (run on 2026-11-22) - Prompt: "Put this exact tea tin on a rustic wooden shelf in a cozy cottage kitchen in the evening, next to a steaming cup of tea and a small vase of dried lavender, warm lamp light. Keep the tin, its label and its lettering exactly the same." - Result: The same tin and label moved onto a rustic shelf with a steaming cup, dried lavender and an oil lamp; lettering unchanged. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/nb2-edit-shelf.webp - Text to image, 3:4, 1K, 1 output: 8 credits, result in 23 s (run on 2026-11-22) - Prompt: "A printed recipe card for "Lemon Ricotta Pancakes" lying on a white marble kitchen counter, photographed from above in soft morning light. The card shows the title at the top, an ingredients list (1 cup ricotta, 2 eggs, 1 lemon, zested, 3/4 cup flour, 1 tbsp sugar) and four short numbered steps in a clean serif font, every word readable. A small stack of pancakes with blueberries sits beside the card. Keep the card and its text in the middle of the frame with counter space around it." - Result: Recipe card on marble with a pancake plate; title, ten ingredients and four steps all legible and spelled right. It wrote a longer ingredient list than the prompt gave (added baking powder, salt, milk, vanilla). - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/nb2-recipe-card.webp - Text to image, 8:1, 1K, 1 output: 8 credits, result in 25 s (run on 2026-11-22) - Prompt: "An ultra-wide panoramic banner of a small Mediterranean harbor town at dawn: pastel houses stacked up a hillside, fishing boats on calm water reflecting a pink and gold sky, a white lighthouse near the right end. Soft morning haze, gentle light, photographic. No text." - Result: Wide 8:1 harbor panorama at dawn (2928 × 352): pastel hillside town, boats, a lighthouse on the right, pink and gold sky, no text. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/nb2-harbor-banner.webp ## Nano Banana 2 Lite - Modes: Text to image, Image to image - Reference images: up to 10 - Aspect ratios: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9, auto - Outputs per run: 1 to 4 - Credits: 4 per image ### Our test runs - Text to image, 4:3, 1 output: 4 credits, result in 11 s (run on 2026-11-22) - Prompt: "A street-food stall at night with a hand-painted sign that reads "MAMA LIN'S DUMPLINGS" and a menu board below it listing: Pork & Chive 6 for $5, Veggie 6 for $4.50, Spicy Wontons $6, Scallion Pancake $3.50. Steam rises from bamboo baskets, warm string lights overhead, a few customers in soft focus. Photographic." - Result: All four menu lines right; added Chinese characters around the English sign; busy market street. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/grid-stall-lite.webp - Text to image, 3:4, 1 output: 4 credits, result in 12 s (run on 2026-11-22) - Prompt: "Portrait photo of an elderly man with a gray beard and a knitted wool cap, sitting by a window, soft natural window light on one side of his face, calm expression, looking slightly off camera. Fine skin texture, shallow depth of field, muted warm tones." - Result: Green cap, brown sweater, seated in a warm cluttered room; looking slightly off camera with a small smile. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/grid-portrait-lite.webp - Text to image, 1:1, 1 output: 4 credits, result in 12 s (run on 2026-11-22) - Prompt: "An isometric 3D miniature of a cozy two-story bookstore cut away to show the inside: tall shelves full of colorful books, a reading nook with an armchair and a lamp, a cat sleeping on the counter, a spiral staircase, plants on the windowsills. Soft studio lighting, clean pale background." - Result: Lighter two-story cutaway with small figures browsing, spiral stairs, green armchair. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/grid-bookstore-lite.webp - Text to image, 16:9, 1 output: 4 credits, result in 15 s (run on 2026-11-22) - Prompt: "A YouTube video thumbnail: a smiling young woman in a yellow raincoat holds up a steaming bowl of ramen in a neon-lit Tokyo alley at night. Big bold white headline on the left that reads "TOKYO ON $30 A DAY" with a thin black outline. High contrast, saturated colors, the woman on the right third." - Result: 16:9 thumbnail: TOKYO ON $30 A DAY spelled right in white with a black outline; woman in a yellow raincoat holding up ramen; dense Japanese neon signs, one stray "DAY" sign in the background. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/lite-thumb-lite.webp ## Nano Banana - Modes: Text to image, Image to image - Reference images: up to 10 - Aspect ratios: 1:1, 9:16, 16:9, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9, auto - Outputs per run: 1 to 4 - Credits: 4 per image ### Our test runs - Text to image, 4:3, 1 output: 4 credits, result in 12 s (run on 2026-11-22) - Prompt: "A street-food stall at night with a hand-painted sign that reads "MAMA LIN'S DUMPLINGS" and a menu board below it listing: Pork & Chive 6 for $5, Veggie 6 for $4.50, Spicy Wontons $6, Scallion Pancake $3.50. Steam rises from bamboo baskets, warm string lights overhead, a few customers in soft focus. Photographic." - Result: Sign right, but the menu shows three items (Veggie is missing) and reads "Scallion Pancke $3.5". - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/grid-stall-nb.webp - Text to image, 3:4, 1 output: 4 credits, result in 11 s (run on 2026-11-22) - Prompt: "Portrait photo of an elderly man with a gray beard and a knitted wool cap, sitting by a window, soft natural window light on one side of his face, calm expression, looking slightly off camera. Fine skin texture, shallow depth of field, muted warm tones." - Result: Close crop of the face by a window, long beard, strong warm tones. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/grid-portrait-nb.webp - Text to image, 1:1, 1 output: 4 credits, result in 11 s (run on 2026-11-22) - Prompt: "An isometric 3D miniature of a cozy two-story bookstore cut away to show the inside: tall shelves full of colorful books, a reading nook with an armchair and a lamp, a cat sleeping on the counter, a spiral staircase, plants on the windowsills. Soft studio lighting, clean pale background." - Result: Fewer shelves and props: armchair, lamp, spiral stairs, cat on the desk. - Image: https://cdn.minimaxh3max.com/assets/landing/nanobananaflash/samples/grid-bookstore-nb.webp ## Veo 3.1 Fast - Modes: Text to video, Image to video, Video to video - Image to video inputs: first frame (required), last frame (optional) - Reference images: up to 3 - Aspect ratios: 16:9, 9:16, auto - Resolutions: 720p, 1080p, 4k - Credits: 60 per clip (720p) to 180 per clip (4k) ### Our test runs - Text to video, 16:9, 720p: 60 credits, result in 68 s (run on 2026-10-21) - Prompt: "A tall guy in a grocery store reaches for the last box of cereal on the top shelf — just as a woman on her tiptoes stretches for the same box from the other side. They both grab it at the same time, look at each other, then burst out laughing. He gestures "go ahead." She hesitates, then splits it — hands him half. Handheld camera, fluorescent supermarket lighting, natural and candid feel." - Result: An 8-second 720p clip: a man and a woman reach for the same cereal box on a top shelf, laugh, and each end up holding a half-open box in the aisle. The box packaging shows garbled text. Audio was generated but not reviewed. - Video: https://cdn.minimaxh3max.com/assets/landing/voo31/veo-3-1-lite-vs-fast/fast-cereal.mp4 ## Veo 3.1 - Modes: Text to video, Image to video - Image to video inputs: first frame (required), last frame (optional) - Aspect ratios: 16:9, 9:16, auto - Resolutions: 720p, 1080p, 4k - Credits: Text to video: 250 per clip (720p) to 380 per clip (4k); Image to video: 250 per clip (720p) to 370 per clip (4k) ## Veo 3.1 Lite - Modes: Text to video, Image to video - Image to video inputs: first frame (required), last frame (optional) - Aspect ratios: 16:9, 9:16, auto - Resolutions: 720p, 1080p, 4k - Credits: 30 per clip (720p) to 150 per clip (4k) ### Our test runs - Image to video, 16:9, 720p, first frame: 30 credits, result in 88 s (run on 2026-11-14) - Prompt: "The small fishing boat moves slowly across the fjord, its wake spreading over the calm green water; a few light snowflakes begin to drift down. The camera pans gently to the right along the red cabins on stilts. Quiet water lapping, a distant boat engine and a few gulls." - Result: 8-second 1280 × 720 clip: the boat crosses the fjord leaving a wake, a gull flies across the sky and the camera drifts right along the red cabins; the snowflakes are faint. Audio was generated but not reviewed. - Video: https://cdn.minimaxh3max.com/assets/landing/nanobananapro/image-to-video/fjord-clip.mp4 - Image to video, auto, 720p, first frame: 30 credits, result in 64 s (run on 2026-11-14) - Prompt: "The mountain stream keeps flowing around the mossy rock; water splashes up around the base of the bottle and droplets fall back into the stream. The camera slowly pushes in towards the bottle. The bottle itself stays still and unchanged. Sound of running water." - Result: 8-second 1280 × 720 clip: the splash grows around the bottle's base and droplets fly while the bottle and its TIDE lettering stay steady. The square picture was cropped to 16:9, cutting off the bamboo cap. Audio was generated but not reviewed. - Video: https://cdn.minimaxh3max.com/assets/landing/nanobananapro/image-to-video/product-clip.mp4 - Image to video, auto, 720p, first frame: 30 credits, result in 70 s (run on 2026-11-14) - Prompt: "Steam curls up from the mug, the leaves outside the window sway in a light breeze, and the patches of sunlight shift slowly across the oak counter. The camera pushes in slowly towards the mug. The mug, its wave pattern and the yellow flowers stay unchanged. Soft morning ambience, birds outside." - Result: 8-second 1280 × 720 clip: a slow push-in on the mug and flowers as the sunlight shifts on the counter; the wave pattern holds and the steam is barely visible. The 4:3 picture was cropped to 16:9. Audio was generated but not reviewed. - Video: https://cdn.minimaxh3max.com/assets/landing/nanobananapro/image-to-video/mug-clip.mp4 ## Seedance 2 - Modes: Text to video, Image to video, Video to video - Image to video inputs: first frame (required), last frame (optional) - Reference images: up to 9 - Reference videos: up to 3 - Reference audio: up to 3 - Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive - Resolutions: 480p, 720p, 1080p, 4k - Duration: 4 to 15 seconds - Credits: Text to video, Image to video: 20 per second (480p) to 210 per second (4k); Video to video: 15 per second (480p, with reference_video_urls) to 190 per second (4k, without reference_video_urls) ## Seedance 2 Fast - Modes: Text to video, Image to video, Video to video - Image to video inputs: first frame (required), last frame (optional) - Reference images: up to 9 - Reference videos: up to 3 - Reference audio: up to 3 - Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive - Resolutions: 480p, 720p - Duration: 4 to 15 seconds - Credits: Text to video, Image to video: 15 per second (480p) to 25 per second (720p); Video to video: 7 per second (480p, with reference_video_urls) to 25 per second (720p, without reference_video_urls) ## Seedance 2 Mini - Modes: Text to video, Image to video, Video to video - Image to video inputs: first frame (required), last frame (optional) - Reference images: up to 9 - Reference videos: up to 3 - Reference audio: up to 3 - Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive - Resolutions: 480p, 720p - Duration: 4 to 15 seconds - Credits: Text to video, Image to video: 4 per second (480p) to 9 per second (720p); Video to video: 3 per second (480p, with reference_video_urls) to 8 per second (720p, without reference_video_urls) ## Seedream 5.0 Flash - Modes: Text to image, Image to image - Reference images: up to 10 - Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2, 21:9 - Resolutions: 1K, 2K - Outputs per run: 1 to 4 - Credits: 3 per image (1K) ### Our test runs - Image to image, 3:4, 1 output, 1K, 1 reference images: 3 credits, result in 16 s (run on 2026-11-10) - Prompt: "Put this same woman on a rainy Tokyo side street at night, neon signs and paper lanterns behind her, wearing a black raincoat and holding a clear umbrella. Keep her face, hair, freckles and nose stud exactly the same. Candid photo, shallow depth of field." - Result: Kept the selfie framing and the face almost exactly, stud and freckles included; the street only shows behind her. Input sent as a JPEG copy of the selfie. - Image: https://cdn.minimaxh3max.com/assets/landing/aipicturegenerator/yourself/me-tokyo-sdflash.webp - Image to image, 3:4, 1 output, 1K, 1 reference images: 3 credits, result in 14 s (run on 2026-11-10) - Prompt: "Turn this into an autumn park photoshoot of the same woman: golden leaves, a camel wool coat and a cream scarf, sitting on a wooden bench in warm late-afternoon light. Keep her face, hair, freckles and nose stud exactly the same." - Result: Same face and stud on the bench in coat and scarf; framing still close to the selfie. Input sent as a JPEG copy of the selfie. - Image: https://cdn.minimaxh3max.com/assets/landing/aipicturegenerator/yourself/me-autumn-sdflash.webp - Image to image, 3:4, 1 output, 1K, 1 reference images: 3 credits, result in 14 s (run on 2026-11-10) - Prompt: "Make this a 1990s high school yearbook portrait of the same woman: mottled blue studio backdrop, soft flash, slight film grain, a denim jacket over a white tee. Keep her face, hair, freckles and nose stud exactly the same." - Result: Face and stud kept; light denim jacket on a blue backdrop. Input sent as a JPEG copy of the selfie. - Image: https://cdn.minimaxh3max.com/assets/landing/aipicturegenerator/yourself/me-yearbook-sdflash.webp - Text to image, 16:9, 1 output, 1K: 3 credits, result in 21 s (run on 2026-11-10) - Prompt: "An anime character sheet of a young woman bike courier with short silver hair, a red bomber jacket, goggles pushed up on her forehead and a messenger bag: front, side and back views standing in a row, plus three small face close-ups (happy, surprised, angry). Clean line art, flat cel shading, plain white background." - Result: Clean sheet: front, side and back views plus three labelled faces; it added a grey hoodie. - Image: https://cdn.minimaxh3max.com/assets/landing/aipicturegenerator/best/best-anime-sdflash.webp ## Tools - Background Remover (image): 1 credit per run - Image Extender (image): 2 credits per run - Image Upscaler (image): 2 credits (2x) or 4 credits (4x) or 8 credits (8x) per run - Photo Restore (image): 6 credits per run - Motion Control (video): 20 credits (720p) or 40 credits (1080p) per second of video, minimum 45 credits per run - Lip-Sync Video (video): 5 credits (720p) or 10 credits (1080p) per second of video, minimum 15 credits per run - Video Upscaler (video): 2 credits (1080p) or 3 credits (2k) or 6 credits (4k) per second of video