SpicyAPI Release Notes

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.

Model Endpoint Price Wan 2.6 Flash Reference to video, silent $0.0225 per second at 720p, $0.03375 at 1080p Wan 2.6 Flash Reference to video, with sound $0.045 per second at 720p, $0.0675 at 1080p

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.

Original source

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.

Model Endpoint Price Qwen Image 2.1 Pro Text to image, image editing $0.036 per image Qwen Image 2.1 Turbo Text to image, image editing $0.0144 per image (was $0.0192) Wan 2.6 Flash Image to video, silent $0.0225 per second at 720p, $0.03375 at 1080p (unchanged) Wan 2.6 Flash Image to video, with sound $0.045 per second at 720p, $0.0675 at 1080p

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.

Original source

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.

Endpoint Per image Text to image $0.0192 Image editing $0.0192

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

Original source

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.

Original source

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.

Model API name LTX 2.3 Spicy lightricks/ltx-2.3-spicy/video-extend LTX 2.3 Spicy LoRA lightricks/ltx-2.3-spicy-lora/video-extend LTX-2 19B lightricks/ltx-2-19b/video-extend MiniMax H3 minimax/h3/video-extend MiniMax H3 LoRA minimax/h3-lora/video-extend MiniMax H3 Max minimax/h3-max/video-extend MiniMax H3 Singularity LoRA minimax/h3-singularity-lora/video-extend MiniMax H3 Spicy minimax/h3-spicy/video-extend Seedance 1.5 Pro bytedance/seedance-1.5-pro/video-extend Seedance 1.5 Pro Spicy bytedance/seedance-1.5-pro-spicy/video-extend Seedance 2.0 bytedance/seedance-2.0/video-extend Seedance 2.0 Fast bytedance/seedance-2.0-fast/video-extend Seedance 2.0 Fast Spicy bytedance/seedance-2.0-fast-spicy/video-extend Seedance 2.0 Mini bytedance/seedance-2.0-mini/video-extend Seedance 2.0 Mini Spicy bytedance/seedance-2.0-mini-spicy/video-extend Seedance 2.0 Spicy bytedance/seedance-2.0-spicy/video-extend Seedance 2.5 bytedance/seedance-2.5/video-extend Seedance 2.5 Spicy bytedance/seedance-2.5-spicy/video-extend Vidu Q3 Spicy vidu/q3-spicy/video-extend Vidu Q3 Turbo vidu/q3-turbo/video-extend Vidu Q4 Preview vidu/q4-preview/video-extend Wan 2.2 LoRA alibaba/wan-2.2-lora/video-extend Wan 2.2 Spicy alibaba/wan-2.2-spicy/video-extend Wan 2.5 alibaba/wan-2.5/video-extend Wan 2.7 Spicy alibaba/wan-2.7-spicy/video-extend Wan 3.0 alibaba/wan-3.0/video-extend Wan 3.0 Prime alibaba/wan-3.0-prime/video-extend Wan 3.0 Prime Spicy alibaba/wan-3.0-prime-spicy/video-extend Wan 3.0 Pro alibaba/wan-3.0-pro/video-extend Wan 3.0 Pro Prime alibaba/wan-3.0-pro-prime/video-extend Wan 3.0 Spicy alibaba/wan-3.0-spicy/video-extend Original source

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.

Original source

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.

Total top-ups Storage Items $10 500 MB 200 $100 1 GB 400 $250 2 GB 800 $1,000 10 GB 4,000

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.

Original source

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.

Family Endpoints Price FLUX.2 Dev LoRA Text to image, edit $0.0216 / $0.036 per image FLUX.2 Klein 9B LoRA Text to image, edit $0.018 / $0.0252 per image FLUX.2 Klein Base 9B LoRA Text to image, edit $0.024 / $0.0312 per image FLUX.2 Klein 4B LoRA Text to image, edit $0.0156 / $0.0204 per image FLUX.2 Klein Base 4B LoRA Text to image, edit $0.018 / $0.024 per image FLUX.1 Krea Dev LoRA Text to image, edit $0.024 per image FLUX.1 Schnell LoRA Text to image, edit $0.006 per image FLUX.1 Fill Dev LoRA Edit inside a mask $0.042 per image FLUX.1 Dev ControlNet LoRA Text to image guided by a control image $0.036 per image Krea 2 Turbo LoRA Text to image, edit $0.0216 at 1k, $0.036 at 2k per image P-Image LoRA Text to image, edit $0.006 / $0.012 per image Qwen Image 1.0 LoRA Text to image, edit $0.03 per image Qwen Image Edit 2509 LoRA Edit with up to three source images $0.03 per image Wan 2.1 Image LoRA Text to image, edit $0.03 per image Wan 2.2 Image LoRA Text to image $0.03 per image Wan 2.1 LoRA Text to video, image to video, video to video $0.24 to $0.54 per clip (5 or 10 seconds, 480p or 720p) Wan 2.2 5B LoRA Text to video, image to video $0.12 per 5-second 720p clip LTX-2.3 LoRA Text to video, image to video, with sound $0.06 per clip plus $0.024 to $0.048 per second

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.

Original source

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

Resolution Before Now 540p $0.054 $0.045 720p $0.114 $0.095 1080p $0.144 $0.12 2k $0.228 $0.19 4k $0.468 $0.39

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.

Original source

Vidu Q4 Preview

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.

Resolution Per second 540p $0.054 720p $0.114 1080p $0.144 2k $0.228 4k $0.468

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.

Original source

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.

| Price per second
|---|---|
| Text or image to video, 720p / 1080p | $0.17 / $0.29 |
| Text or image to video, draft (720p) | $0.06 |
| Video extend, 720p / 1080p | $0.41 / $0.53 |
| Video extend, draft (720p) | $0.12 |
| Video upscale, precise / creative | $0.528 / $0.7584 per second of input |

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.

Original source

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.

Model Text to image, 1k / 2k Edit FLUX.2 Max $0.07 / $0.0881 $0.0761 FLUX.2 Pro $0.03 / $0.0391 $0.0578 FLUX.2 Flex $0.0578 / $0.0881 $0.1154 FLUX.2 Dev $0.0116 / $0.0116 $0.0231 FLUX.2 Klein 9B $0.011 / $0.0122 $0.0163 FLUX.2 Klein 4B $0.0093 / $0.0099 $0.0126

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.

Original source

Claude Haiku 5.5, released by Anthropic on 7 October, is now on SpicyAPI as one OpenAI-compatible chat endpoint: anthropic/claude-haiku-5.5/chat.

Claude Haiku 5.5 Input / output, prompts up to 100,000 tokens | $0.10 / $0.50 per million tokens Input / output, prompts over 100,000 tokens | $0.50 / $2.50 per million tokens Context window / longest reply | 1,000,000 / 128,000 tokens Message content | Text and images Tool calls | Up to 128 tools; tool_choice can force a call

Content tests

We add no filter of our own. In 24 test requests on 8 October the model wrote 20 in full, toned 2 down and refused 2. An intimate scene between two adults came back complete in 8 of 9 attempts; the refusals were explicit, part-by-part figure studies.

Good to know

The model decides how much to think, so there is no reasoning_effort; there is no stop or temperature either. max_tokens does not cut the reply short: ask for the length you want in the prompt, and you pay for the tokens actually written. Cache hits cost $0.10 per million tokens.

Short answers came back in three to five seconds in our tests. Failed requests are not charged.

Original source

Google released Nano Banana 2.1 on 6 October 2026, an update to Nano Banana 2 (Gemini 3.1 Flash Image) with better image quality, prompt adherence, character consistency across edits and text rendering. Two endpoints are live today:

• Text to image (google/nano-banana-2.1/text-to-image): 1K, 2K or 4K in fourteen shapes from 1:8 to 8:1, PNG or JPEG, with optional web search and image search. In our tests every line of text we put in quotes came out spelled as written, and web search let a forecast poster print the correct date.
• Edit (google/nano-banana-2.1/edit): one to fourteen source images, with faces and product details kept; auto keeps the source shape.

Google's content policy applies: suggestive fashion renders, while nudity requests come back toned down in text to image and are refused in editing (refused edits are not charged).

Size tier Per image 1k $0.048 2k $0.072 4k $0.162

Editing adds $0.0024 per source image; web search and image search add $0.0168 each when switched on.

Original source