Updates that matter when you build

Wan 2.6 Flash, the faster and lower-cost tier of Alibaba's Wan 2.6, now has a second endpoint on SpicyAPI: reference to video.

• Wan 2.6 Flash, reference to video (alibaba/wan-2.6-flash/reference-to-video): up to five references, up to three of them short clips and the rest still images, or stills alone. Name them in the prompt as character1, character2 and so on, and the model casts them into a new scene of 2 to 10 seconds at 720p or 1080p, in five aspect ratios.
• Sound is a switch. generate_audio is off by default; turn it on and the clip comes back with generated voices, effects and ambience at twice the per-second rate.
• Still images are free. Reference clips add their seconds to the bill, counted up to five seconds in total.

There is no content filter in front of the endpoint, and prompt expansion is off by default so your prompt reaches the model as written. None of our test requests was refused.

Billable seconds are the output length plus the reference clips, each rounded up to whole seconds, with the clips counted up to five seconds in total.

Qwen Image 2.1 Pro, the hosted Pro tier of Alibaba's Qwen Image 2.1, can now be called on SpicyAPI, and two models already in the catalog change today.

• Qwen Image 2.1 Pro, text to image (alibaba/qwen-image-2.1-pro/text-to-image): one to six images per request in fifteen aspect ratios at 1k, 1.5k or 2k. Our requests took 14 to 43 seconds.
• Qwen Image 2.1 Pro, image editing (alibaba/qwen-image-2.1-pro/edit): one to ten reference images and a plain-language instruction. Leave the aspect ratio out and the result keeps your source's shape at about 2K.
• Qwen Image 2.1 Turbo now costs $0.0144 an image on both endpoints, down from $0.0192.
• Wan 2.6 Flash image to video has a new generate_audio switch. Off, the default, the clip stays silent at the same per-second price as before; on, it comes back with a generated soundtrack at twice the rate.

There is no content filter in front of Qwen Image 2.1 Pro, and prompt expansion is off by default so your prompt reaches the model as written. Not one of our test requests was refused.

For both Qwen models every resolution tier costs the same, each image returned is billed, and the number of reference images does not change the price.

Qwen Image 2.1 Turbo, the 8-step checkpoint of Qwen Image 2.1 that Alibaba's Qwen team released with open weights on 9 October 2026, can now be called on SpicyAPI. The page that showed it as coming soon now runs it.

• Text to image (alibaba/qwen-image-2.1-turbo/text-to-image): one to six images per request in fifteen aspect ratios at 1k, 1.5k or 2k. Our requests took 13 to 39 seconds.
• Image editing (alibaba/qwen-image-2.1-turbo/edit): one to ten reference images and a plain-language instruction. Leave the aspect ratio out and the result keeps your source's shape at about 2K.

There is no content filter in front of either endpoint. Prompt expansion is off by default: with it on, Alibaba's rewrite tones adult prompts down, and in our tests an edit asking a clothed portrait to reveal more came back unchanged.

Every resolution tier costs the same, each image returned is billed, and the number of reference images does not change the price.

There is a new page for making one consistent character: AI Influencer Generator. Pick a look, keep the face you like, and everything you make after that starts from the same person.

• Pick or describe. Choose from 17 trait lists with 162 options, each shown with a small picture: gender, age, heritage, skin tone, build, face shape, hairstyle, hair color, eye shape, eye color, facial features, facial hair, distinctive features, makeup, style, accessories and expression. Anything you leave empty is up to the model. Prefer to write? Describe the look in one sentence and it is sent exactly as you wrote it.
• 36 sample characters. Open a sample and press Use these traits to copy its picks, then change what you want. Or press Surprise me.
• Each candidate is two photos. A close-up and a full-length photo of the same person on a plain background, made with Seedream 5.0 Pro at $0.036 per photo, so $0.072 per candidate. Make 1 to 4 candidates at a time. The price is on the button before you run.
• Change one thing. Write a short line such as "make the hair shoulder-length" and get a new candidate where only that detail changes.
• Save it once. Name the character and save it. Both photos go to your asset library, and the character shows up in Characters across Studio. The asset library opens once you have topped up $10 or more in total.
• Character home. Open a saved character and choose what to make: a Photo set in new places, outfits and poses; a New look from one sentence, in three versions; Make a video from the cover photo; Talk, a lip-synced clip from a line you write and a voice you pick; or Copy a move from a 2 to 30 second reference clip. Every card shows its price.

Every character here is an original, fictional adult. Ages start at the 20s and there are no teen options. To build a character from your own photos instead, use New character in your asset library, which asks you to confirm the photo is yours or that you have the person's permission.

You can now continue a video you already have. Upload a clip, say what happens next, and SpicyAPI generates a new segment from the last frame of your clip and joins both into one MP4. It works on 31 video model families, in the API and on the site.

• How it works. Send your clip as video_url (MP4, MOV or WebM, up to 60 seconds) and a short prompt describing what happens next. On most models the prompt is optional. You get back the joined MP4 and, separately, the new segment on its own. You can extend the joined result again as many times as you like.
• Optional end frame. Some models accept last_image_url, a frame you want the new segment to end on. Seedance 2.5 reads up to the last 30 seconds of your clip as reference, so the new segment follows the motion more closely.
• Pricing. You pay only for the new segment, at that model's image-to-video price. Your original clip is not charged. Seedance 2.5 also charges for the seconds of reference it reads, at the same price as its reference-to-video. If joining fails, the whole job is refunded.
• A clean seam. Color, brightness and volume of the new segment are matched to your clip, and the frame rate follows your clip. No black bars are added. To line the seam up, the picture may be cropped or adjusted by a few percent at the edges.
• On the site. In Playground, Studio, Assets, the task history in the console and the short film editor, every video result has a one-click Extend button. Your clip is filled in, the same model is selected, and the price sits next to the button.
• 4K HDR clips. Phone footage in 4K HDR has a length limit: about 15 seconds at 60 fps and about 40 seconds at 30 fps. 1080p HDR is not affected.

FLUX 3 and Wan 2.2 Spicy LoRA already had their own native extend and keep it. The new endpoints are the video-extend model of each family below.

Your Assets library now has its own page at spicyapi.ai/assets, and it is the same library you see in Studio. Everything you keep lives there: saved results, uploads and characters.

• Folders. Group what belongs together. Drag items onto a folder in the sidebar, or use Add to folder.
• Favorites. Tap the heart on anything you reach for often.
• Characters. Put a few photos of the same person together and give them a name, then @ that name in your prompt. Characters you already made in Studio moved in automatically, with nothing to redo, and they no longer have their own limit: they count toward your library storage like everything else.
• Create with this. Every item and every character opens straight into Studio with the reference already in place, on a model page with the reference field filled in, or as ready-to-copy API code.

For developers, GET /api/v1/assets now filters by favorite and folder and sorts by date, name or size, and characters can be read through GET /api/v1/assets/entities. Old spicy://p/ references keep working. Details are in the docs: Asset library.

You can now keep the images, videos and audio you reuse, such as a character's reference photos, in Assets and drop them into any request as spicy://a/<id>. The same library works in the Playground, in Studio and through the API.

• Save from anywhere. Bookmark a result, upload files, or save from the API with POST /api/v1/assets (from a finished task, an upload or a public link). Turn on auto-save in Assets to keep everything you generate on the website.
• Private by design. Assets stay until you delete them. Previews are short-lived links signed for you alone, and nothing in the library gets a public URL.
• Team libraries. Each team workspace has its own shared library. The team's API keys read and save there, and roles decide who can add or delete.

Also new:

• Point at your references in the prompt. Type @ to insert a reference image, video, audio clip or named element, written the way each model expects. On Seedream 5.0 you can mark a point or a box on a reference image, and inpainting endpoints let you draw the mask right in the form.
• MiniMax H3 reference to video now takes up to 3 reference videos (15 seconds in total) and up to 3 audio clips. Reference video seconds now have their own lower rate ($0.0231 per second at 768p, $0.0378 at 2K), the first five reference images stay free, and each image from the sixth costs $0.014.
• Studio opens faster, lists video first, and takes reference videos and audio alongside your photos.

API details are in the docs: Asset library.

Eighteen LoRA-ready model families joined the catalogue today, 33 endpoints in all. Each one loads your own LoRA files by direct link at no extra charge (up to three per request on most, one on P-Image), and the platform adds no content filter.

Before you plug a LoRA in:

• Match the base. A LoRA only works on the base model it was trained for. One made for a different base usually loads without an error and changes nothing, so check its model card first. Every model page lists what we tested.
• Use a direct link to the weights file. A link to a repository page, or to a file that needs a login, fails with a clear error and is not charged.
• Start at scale 1. Strengths well above 1 quickly degrade the picture.

Open any of the new families under Models for tested results, example prompts and the full price table.

From 9 October 2026, both Vidu Q4 Preview endpoints cost about 17% less, the same per-second rates as Vidu's own list price.

Prices are per second of output, for vidu/q4-preview/image-to-video and vidu/q4-preview/reference-to-video.

• Nothing to change on your side. Requests, resolutions and durations are unchanged, and the estimate before you submit and the charge afterwards use the new rates. Sound on or off and the number of references still do not change the price.
• Vidu tightened image to video the same day. A request for an intimate scene between two adults, which came back only implied on 8 October, is now refused, and refused requests are not charged. Topless and consensual restraint still came through in our retest.

Vidu Q4 Preview, the public preview of Vidu's Q4 video model (released 7 October 2026), is now on SpicyAPI with two endpoints. Clips run 3 to 16 seconds at 540p up to 4k, with dialogue, effects and ambience generated alongside the picture; write a line in double quotes and it is spoken.

• Image to video (vidu/q4-preview/image-to-video): start from one opening frame; the clip keeps its shape. In our content tests it was never refused.
• Reference to video (vidu/q4-preview/reference-to-video): 1 to 15 reference images of people, outfits, products or places plus up to 3 voice clips become one scene. It refuses nudity and sex scenes, and refused requests are not charged.

2k and 4k come back as 10-bit HEVC files, which some browsers cannot play inline. Sound on or off and the number of references do not change the price.

FLUX 3, the video model from Black Forest Labs, is now on SpicyAPI with four endpoints: text to video, image to video (with an optional last frame), video extend and video upscale.

Text to video, image to video and extend are at Black Forest Labs' list price.

Clips with sound. Videos run 5 to 20 seconds with synchronized audio, and sound on or off costs the same. Draft is a fast, low-cost preview tier at 720p: use it to try a prompt, then render the one you keep at full quality.

Extend and upscale. Extend takes a clip of up to 15 seconds and writes 5 to 20 new seconds from its last frame; you get the new segment only. Upscale enlarges a clip of up to 20 seconds by 1.5 to 3 times and keeps its sound: precise only sharpens, creative also rebuilds fine detail.

Content tests. We add no filter of our own. FLUX 3 runs Black Forest Labs' own moderation: suggestive scenes come back, anything more revealing is refused. Failed or refused requests are not charged.

Six FLUX.2 models from Black Forest Labs are now on SpicyAPI, each with a text-to-image and an edit endpoint: FLUX.2 Max, Pro, Flex, Dev, Klein 9B and Klein 4B.

Prices are per image. Aspect ratio does not change the price, and an edit costs the same whether you send one reference image or three.

What each one is for. Max is the flagship for the best detail. Pro is the everyday workhorse. Flex is strongest on typography and text inside the image. Dev is the 32B open-weight model. Klein 9B and 4B are small distilled models that return an image in well under a minute.

Content tests. We add no filter of our own. Max, Pro and Flex run Black Forest Labs' own moderation: suggestive images come back, more revealing requests are usually covered up or refused, and edits of people are refused more often than text to image. Dev and the two Klein models are open-weight with no moderation, and nothing was refused in our tests, though the smaller models often add clothing on their own.

Every model takes nine aspect ratios at 1k (about one megapixel) or 2k (2048 px on the long side), and up to three reference images for edits. Failed or refused requests are not charged.