> ## Documentation Index
> Fetch the complete documentation index at: https://docs.budgetpixel.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> New models, endpoints, price changes and retirements in the BudgetPixel API and MCP server, newest first.

Prices are the standard credit prices at release, before any plan discount. [`GET /v1/models`](https://docs.budgetpixel.com/api-reference/models/list-available-models) always returns the current ones, and [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) quotes a request before you send it.

**November 19, 2026**

## Kling Image 4.0 and Kling Image 4.0 Long

[`POST /v1/images/kling-image-4.0`](https://docs.budgetpixel.com/api-reference/kling/generate-image-with-kling-image-40): Kling's newest image model, with realistic images, correctly spelled text and edits that combine up to 10 reference images (refer to them in the prompt as `@image_1`, `@image_2` …).

* `size` `2K` (the default, about 4 MP) or `4K` (5440x3072 at 16:9); `aspect_ratio` is `auto` (the default: the model chooses) or one of `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `21:9`.
* `num_images` (1–4), each generated and billed independently. No seed or negative prompt.

[`POST /v1/images/kling-image-4.0-long`](https://docs.budgetpixel.com/api-reference/kling/generate-image-with-kling-image-40-long): one tall image, 1024 px wide: a full webpage design (`skill: "webpage"`) or an ecommerce product detail page made from 1–3 product photos (`skill: "ecommerce"`, `length` `short`, `medium` or `long`). For a webpage, `reference_images` takes up to 2: the subject first, then a style reference. The page's text follows the prompt's language.

**Pricing.** Kling Image 4.0: `2K` 75, `4K` 115 credits per image. Kling Image 4.0 Long: a webpage 675; a product page 290 (`short`), 580 (`medium`) or 965 (`long`). Both add 4 credits for each reference image, per generated image.

**MCP.** Both are in `list_models` and `generate_image` (`skill` and `length` for the Long model).

**November 18, 2026**

## MAI Image 2.7

[`POST /v1/images/mai-image-2.7`](https://docs.budgetpixel.com/api-reference/microsoft/generate-image-with-mai-image-27): Microsoft's newest image model, with realistic photos, correctly spelled text in images, and precise edits from plain instructions that change what you ask and keep the rest. Text-to-image, plus editing and combining up to 5 input images.

* `size` `1K` (the default, about 1 MP) or `2K` (about 4 MP); `aspect_ratio` is `auto` (the default: an edit keeps its first input's frame and comes back aligned with it; text-to-image is `1:1`) or one of `1:1`, `4:3`, `3:4`, `3:2`, `2:3`, `16:9`, `9:16` (on an edit, a ratio other than the input's own re-composes the picture into that shape).
* `background: "transparent"` returns a cut-out (PNG, or WebP with `output_format: "webp"`) from a text prompt. With input images the model draws the subject anew; it is not a background remover.
* `num_images` (1–4), each generated and billed independently. Prompts up to 8,000 characters. No seed or negative prompt.

**Pricing.** Per image by size: `1K` 50, `2K` 190 credits, plus 11 (`1K`) or 45 (`2K`) credits for each input image, per generated image.

**MCP.** `mai-image-2.7` is in `list_models` and `generate_image`.

**November 16, 2026**

## Mureka V9.5

[`POST /v1/audios/mureka-v9.5`](https://docs.budgetpixel.com/api-reference/music/generate-music-with-mureka-v95): Mureka V9.5, Mureka's newest music model. The same inputs as `mureka-v9`: a song sings your `lyrics` word for word (up to 5,000 characters, with `[verse]` / `[chorus]` tags), with an optional style `prompt` (up to 1,024 characters) and `vocal_gender`; set `instrumental: true` for an instrumental made from the `prompt`. One MP3 per request.

**Pricing.** 200 credits per song or instrumental, a flat price whatever its length. `mureka-v9` stays at 60.

**MCP.** `generate_music` takes `model: "mureka-v9.5"`.

**November 16, 2026**

## SeeDance 2.5 at 4K

[`POST /v1/videos/seedance-2.5`](https://docs.budgetpixel.com/api-reference/bytedance-seedance/generate-video-with-seedance-25) takes `resolution: "4k"`: 3840 × 2160 at 16:9, 2160 × 3840 at 9:16 and 2880 × 2880 square, with every mode (text, frames, references, editing and extension) and any length from 4 to 30 seconds.

* 4K output is H.265 (HEVC), 10-bit, like `1080p`. See [video output format](https://docs.budgetpixel.com/concepts/models.md#video-output-format).
* Draft mode stays 480p, with its final at 1080p.

**Pricing.** 1250 credits per second of output, plus 750 per second of reference-video input. [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) quotes it.

**MCP.** `generate_video` takes `resolution: "4k"` on `seedance-2.5`.

**November 16, 2026**

## SeeDance 2.5 and 2.5 Flash: `aspect_ratio` with reference videos

On [`seedance-2.5`](https://docs.budgetpixel.com/api-reference/bytedance-seedance/generate-video-with-seedance-25) and `seedance-2.5-flash`, an `aspect_ratio` you send with `reference_videos` now sets the output's shape. Leave it out and the model picks one (adaptive), as before. A job the model reads as an edit or an extension of a reference clip keeps that clip's shape, and a start frame (`image`) still sets the shape on its own.

**November 15, 2026**

## SeeDance 2.5 Flash

[`POST /v1/videos/seedance-2.5-flash`](https://docs.budgetpixel.com/api-reference/bytedance-seedance/generate-video-with-seedance-25-flash): SeeDance 2.5 Flash, ByteDance's faster, lower-cost SeeDance 2.5. Text-to-video, start and end frames, and reference-to-video from up to 10 images, 5 video clips and 5 audio clips, which also edits or extends a clip. 480p or 720p with generated sound, 4–30 seconds.

* **Pricing:** 93 credits per second of output at 480p, 200 at 720p. Reference videos add 57 (480p) or 123 (720p) credits per second of input. [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) quotes any request.
* For 1080p or draft mode, use `seedance-2.5`.

**MCP.** `seedance-2.5-flash` is in `list_models` and `generate_video`.

**November 13, 2026**

## Kling 4.0 Flash, new Kling 3.0 prices, two Kling models retired

[`POST /v1/videos/kling-v4-flash`](https://docs.budgetpixel.com/api-reference/kling/generate-video-with-kling-40-flash): Kling 4.0 Flash, the faster, lower-cost Kling 4.0. 720p with generated sound, 3–20 seconds, from text, a first frame, up to 10 reference images, or a video to edit.

* **Pricing:** 123 credits per second of output. With an input video, 82 credits per billed second: twice the output when the input is shorter than the output, otherwise input plus output.
* **Kling 3.0 prices changed:** Standard 219 credits per second (328 with audio), Pro 292 (437), 4K 546. Kling 3.0 Omni is 219 at 720p, 292 at 1080p and 546 at 4K (292 and 364 with audio at 720p and 1080p). An Omni edit bills each second of the input clip (3–10 s): 219 at 720p, 292 at 1080p. Kling 3.0 and Omni take 3–15 seconds and prompts of up to 2,500 characters. [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) quotes any request exactly.
* **Retired:** `kling-v2.6-pro` and `kling-3.0-turbo` answer `410 model_retired`. Use `kling-4.0` and `kling-v4-flash` instead.

**MCP.** `kling-v4-flash` is in `list_models` and `generate_video`.

**November 13, 2026**

## Eleven Music v2.5

[`POST /v1/audios/eleven-music-v2.5`](https://docs.budgetpixel.com/api-reference/music/generate-music-with-eleven-music-v25): ElevenLabs' newest music model. Songs with vocals in many languages, or instrumentals, from a text prompt; `lyrics` are sung as written.

* `prompt` (required, up to 2,000 characters), `lyrics` (optional, up to 3,000; the two together up to 4,090), `instrumental` (not with `lyrics`), `duration` 10–300 seconds (default 60). MP3 output.
* Prompts that name real artists, songwriters, songs, albums or record labels, or quote a real song's lyrics, are refused with a suggested rewrite. Refused jobs are not billed.

**Pricing.** 200 credits per minute of the requested `duration`, billed per second with a 10-second minimum: 30 s = 100, 60 s = 200, 180 s = 600 credits. `GET /v1/models` returns `credits_per_unit: 200` with `unit_type: minute`, and [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) quotes the exact price.

**MCP.** `eleven-music-v2.5` is in `list_models` and `generate_music`, with `duration`, `lyrics` and `instrumental`.

**November 13, 2026**

## MiniMax H3 Image

[`POST /v1/images/minimax-h3-image`](https://docs.budgetpixel.com/api-reference/minimax/generate-image-with-minimax-h3-image): MiniMax's image model, with exact text on signs, menus and posters, natural light and fine detail. Text-to-image, plus editing and multi-reference composition from up to 10 reference images.

* `size` `2K` (the default) or `4K`; `aspect_ratio` is `auto` (the default: an edit keeps its first reference's shape) or one of 13 shapes from `9:21` to `21:9`.
* `num_images` (1–4) are made in one call; an image the model's safety check withholds is not billed.
* No seed, negative prompt or transparent background.

**Pricing.** Per image by size: `2K` 34, `4K` 100 credits, plus 12 credits for each reference image, per generated image.

**MCP.** `minimax-h3-image` is in `list_models` and `generate_image`.

**November 10, 2026**

## Seedream 5.5

[`POST /v1/images/seedream-5.5`](https://docs.budgetpixel.com/api-reference/bytedance/generate-image-with-seedream-55): ByteDance's newest Seedream, with more natural light, materials and skin, sharper small and dense text, and edits that change what you ask and keep the rest of the picture as it was. It generates from text and edits or combines up to 10 `reference_images`.

* `background: "transparent"` returns a cut-out PNG from a text prompt alone or from references. See [transparent backgrounds](https://docs.budgetpixel.com/concepts/models.md#transparent-backgrounds).
* `size` `1K` or `2K` (the default); `aspect_ratio: "match_input_image"` keeps an edit's shape. `output_format` takes `png` (the default) or `jpeg`.
* No grouped generation: `num_images` (1–4) makes each image separately.

**Pricing.** Per image by size: `1K` 26, `2K` 46 credits, plus 10 credits for each reference image, per generated image.

**MCP.** `seedream-5.5` is now the default model of `generate_image` (it was `seedream-5.0-pro`), `background: "transparent"` included.

**November 4, 2026**

## GPT Image 2.6 Flare and Sunburst

[`POST /v1/images/gpt-image-2.6-flare`](https://docs.budgetpixel.com/api-reference/openai/generate-image-with-gpt-image-26-flare) and [`POST /v1/images/gpt-image-2.6-sunburst`](https://docs.budgetpixel.com/api-reference/openai/generate-image-with-gpt-image-26-sunburst): OpenAI's GPT Image 2.6. Flare is the fast one; Sunburst is for dense text, complex layouts and precise edits. Both generate from text and edit or combine up to 16 `reference_images`.

* `complexity` (`low`, `medium` or `high`, the default) sets how much the model plans before it renders. It does not change the price.
* `background: "transparent"` returns a cut-out with a transparent background, from text or an edit, as a PNG (or a WebP). See [transparent backgrounds](https://docs.budgetpixel.com/concepts/models.md#transparent-backgrounds).
* Sizes: 1:1 at `1K` or `2K`, 16:9 and 9:16 at `2K` or `4K` (3840 × 2160), the other ratios at one size. `aspect_ratio: "auto"` lets the model choose, and an edit keeps its picture's shape. `output_format` also takes `webp`.

**Pricing.** Per image by `quality`, the same at every size and with any number of references: low 70, medium 120 (the default), high 175, xhigh 340, max 675 credits.

**Catalog.** Image models priced by quality now list each tier's price as `quality_pricing` in the model catalog the MCP server reads, and the MCP's `list_models` shows it.

**MCP.** `generate_image` takes both models, `background: "transparent"` included.

**November 2, 2026**

## SeeDance 2.5 draft mode: a 480p draft first, then its 1080p final

[`POST /v1/videos/seedance-2.5`](https://docs.budgetpixel.com/api-reference/bytedance-seedance/generate-video-with-seedance-25) can make a cheap draft and, once you like it, render the same video at 1080p: the same motion, framing and sound, sharper. See [draft mode](https://docs.budgetpixel.com/concepts/models.md#draft-mode-a-480p-draft-then-its-1080p-final).

* `draft: true` makes a 480p draft. [`GET /v1/videos/{id}`](https://docs.budgetpixel.com/api-reference/videos/get-video-job-status) on it returns `draft_finalizable`, `draft_expires_at` and `draft_final_credits`.
* `from_draft_job_id`, the draft's `id` sent on its own, renders its 1080p final within 7 days. The final reuses the draft's prompt, inputs, length, aspect ratio, seed and audio setting, and its job returns `from_draft_job_id`. Drafts made in the Video Workshop or over MCP work too.
* `prompt` is no longer required when `from_draft_job_id` is sent.

**Pricing.** A draft is priced like any 480p video: 150 credits per second, plus 80 per second of reference-video input. Its final is priced like a 1080p video of the draft's length: 750 per second, plus 375 per second of the draft's reference-video input. A 5-second draft costs 750 credits and its final 3,750. [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) quotes both; send `from_draft_job_id` to price a final.

**MCP.** `generate_video` takes `draft` on `seedance-2.5`, and the new `finalize_video_draft` tool makes a draft's 1080p final from its `job_id`. `check_generation_status` shows a finished draft's final price and deadline.

**November 1, 2026**

## Wardrobe: dress a character in a chosen outfit

Write an outfit's `@handle` next to a character in any image or video prompt and the character wears exactly those clothes: `"@barry wearing @camel_belted_overcoat_outfit on a rainy street"`. Up to 4 outfits per generation, beside up to 4 characters; their pictures count as reference images. A free library of outfits comes with every account, and you can make your own from a photo or a description on the web. See the [Wardrobe guide](https://docs.budgetpixel.com/wardrobe.md).

* [`GET /v1/wardrobe`](https://docs.budgetpixel.com/api-reference/wardrobe/list-outfits-you-can-use) lists the outfits you can use: yours, the ones you saved and the free library. Free.
* [`GET /v1/wardrobe/{handle}`](https://docs.budgetpixel.com/api-reference/wardrobe/get-an-outfit) gives one in full, with its full-size picture. Free.

**MCP.** `search_wardrobe` and `get_wardrobe_item` find outfits; `generate_image` and `generate_video` take the same @mention.

**October 28, 2026**

## Kling 4.0

[`POST /v1/videos/kling-4.0`](https://docs.budgetpixel.com/api-reference/kling/generate-video-with-kling-40): Kuaishou's Kling 4.0, with generated sound, in one endpoint: text-to-video, a first and an optional last frame, up to 10 reference images, reference videos, and editing a `video` (the output keeps its length and shape). 720p or 1080p, 3 to 30 seconds, 24 fps. Name inputs in the prompt as `@image_1`, `@video_1` and so on.

**Pricing.** 207 credits per second at 720p and 310 at 1080p. With any input video, 124 / 186 per billed second, where the billed seconds are the output plus the longer of the input videos and the output: editing a 5-second clip bills 10 seconds.

**MCP.** `generate_video` takes `kling-4.0` with all of its inputs: frames and reference images combine, and `video` edits a clip.

**October 23, 2026**

## Meshy 7.1: pick the move your character performs

* `animation_move` on [`POST /v1/3d/meshy-7.1`](https://docs.budgetpixel.com/api-reference/3d-models/generate-a-3d-model-with-meshy-71) picks the move an animated character performs: one of about 650 from [`GET /v1/3d/moves`](https://docs.budgetpixel.com/api-reference/3d-models/list-3d-model-moves) (dances, waves, cheers, walks, stunts and fights). Free; without it the move is 92, Double Combo Attack, as before.
* Rigged jobs now also return a walk and a run: `walking_glb`, `walking_fbx`, `running_glb` and `running_fbx` in `files`.

**MCP.** `generate_3d_model` takes `animation_move` on `meshy-7.1` (it turns rigging and animation on by itself).

**October 22, 2026**

## More reference inputs for SeeDance; Wan 3.0 bills reference video

* **SeeDance 2.0, 2.0 Fast and 2.0 Mini** take `reference_videos` (up to 3, 15s combined, billed per input second at half the output rate) and `reference_audios` (up to 3 with `audio`, 15s combined, free) next to up to 9 `reference_images`. With a `video` to edit, up to 2 more `reference_videos` can join it (the `video` is "Video 1"), and edits take up to 9 reference images (was 6).
* **SeeDance 2.5** takes up to 30 `reference_images`, 10 `reference_videos` and 10 `reference_audios` (was 15 / 5 / 5), and a clip may run up to 30 seconds (still 30s combined per kind).
* **Wan 3.0 and Wan 3.0 Prime** now bill reference-video input per second at the output rate, as they bill output: a 5-second 720p edit guided by an 8.2s clip costs `(5 + 9) × 120 = 1680` credits (was 600). Reference images and audio stay free. [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) quotes it exactly.

**MCP.** `generate_video` takes `reference_videos` and `reference_audios` on `seedance-2.0`, `seedance-2.0-mini`, `wan-3.0-video` and `wan-3.0-video-prime`, with the caps above.

**October 20, 2026**

## Characters: cast AI influencers with an @mention

Write `@handle` in an image or video prompt to cast a character: one of the free BudgetPixel AI influencers, or a character of your own. Its picture and look go with the mention, so the same face appears in every post.

* @mentions in the `prompt` of every image and video model that takes characters (each such model's `prompt` says so). `@handle.tag` casts a specific picture; up to 4 characters per generation. Create responses list the cast in `characters`, and [`POST /v1/cost`](https://docs.budgetpixel.com/api-reference/models/estimate-the-cost-of-a-request) counts them.
* [`GET /v1/characters`](https://docs.budgetpixel.com/api-reference/characters/list-characters-you-can-cast): the characters you can cast, influencers first, with `q` and `source` filters.
* [`GET /v1/characters/{handle}`](https://docs.budgetpixel.com/api-reference/characters/get-a-character): one character in full, with the look word for word, the profile, directing notes and every picture with a download link (full size for the influencers and your own characters).
* [`POST /v1/characters/recommend`](https://docs.budgetpixel.com/api-reference/characters/recommend-influencers-for-a-brief): the influencers who fit a brief, each with why, an idea and a ready-to-use prompt.
* The influencers are never shown nude or in sexual content: such requests are refused with `restriction_reason: "official_character_nudity"`. Suggestive outfits and poses are fine.

**Pricing.** The character endpoints are free, with daily limits per account: 300 list calls, 100 character calls and 30 recommendations. Casting adds no fee; a character's picture counts as a reference image, which a few models price per image.

**MCP.** New tools `list_characters`, `get_character` and `recommend_influencers`; `generate_image` and `generate_video` cast characters from @mentions in the prompt.

Guide: [AI influencers and characters](https://docs.budgetpixel.com/characters.md).

**October 18, 2026**

## Job timing, prompt, output expiry and Retry-After on every 429

Job status responses now say when a job started and finished, return its prompt and say when its files expire, and every `429` carries `Retry-After`.

* [`GET /v1/images/{job_id}`](https://docs.budgetpixel.com/api-reference/images/get-image-job-status) and [`GET /v1/audios/{job_id}`](https://docs.budgetpixel.com/api-reference/audios/get-music-job-status): new `prompt`, `started_at` and `completed_at`. `started_at` minus `created_at` is the time the job waited in the queue. Video jobs already returned all three.
* Image, video and audio job status: new `expires_at`, 24 hours after `created_at`, and `expired`. After `expires_at` the files are deleted and the response returns no URLs, where it used to return URLs that answered `403`. Each signed URL is valid for at least 6 hours; call the status endpoint again for fresh ones.
* [`GET /v1/videos/{job_id}`](https://docs.budgetpixel.com/api-reference/videos/get-video-job-status) now returns `id`, like the create response and the API reference. `job_id` stays, with the same value.
* Every `429` sends `Retry-After`. A full concurrency queue sends a suggested wait (5 seconds for images, 10 for audio, 15 for video) and the same body for images, video and audio: `code: "queue_full"`, `queue_limit`, `active_jobs` and `retry_after_seconds`. The monthly spend limit sends the seconds until the month resets, and the posting limits send the time until you can post again.
* A full queue is now refused before your inputs are fetched or checked, so the `429` comes back at once instead of after a few seconds. Simultaneous requests can no longer start more jobs than your concurrency cap.
* When your monthly spend limit is reached, job status, `GET /v1/models`, `GET /v1/account/credits` and `POST /v1/cost` keep working, so you can still collect jobs that started before the limit.

**Pricing.** No change.

Guides: [Output retention](https://docs.budgetpixel.com/concepts/async-jobs.md#output-retention), [Rate limits](https://docs.budgetpixel.com/concepts/rate-limits.md).

**October 17, 2026**

## Depth maps: face mesh

Depth maps can now carry each face's mesh, so a video model given the depth map keeps lip, eye and head movement. Faces are found automatically.

* [`POST /v1/depth-maps/video-depth-anything`](https://docs.budgetpixel.com/api-reference/depth-maps/make-a-depth-map-with-video-depth-anything): new `face_mesh` (draws the mesh over each face), `max_faces` (1 to 4, default 4) and `include_face_landmarks` (returns a JSON file of 478 landmarks, 52 expression scores and head pose per face per frame).
* [`GET /v1/depth-maps/{id}`](https://docs.budgetpixel.com/api-reference/depth-maps/get-depth-map-job-status): new `face_mesh` (how much of the clip had a face, and each face's frames) and `face_landmarks_url`.

**Pricing.** No extra charge: the price is still per second of the input video, by `size`.

**MCP.** `generate_depth_map` takes `face_mesh`, `max_faces` and `include_face_landmarks`; `check_generation_status` returns the face coverage and the landmarks link.

Guide: [Face mesh](https://docs.budgetpixel.com/apis/depth-maps-api.md#face-mesh).

**October 17, 2026**

## Depth maps: Video Depth Anything

Turn a video into a depth map video: in the default grayscale, near is white and far is black, and the result is steady from frame to frame. Use it as a structure or motion reference for video models.

* [`POST /v1/depth-maps/video-depth-anything`](https://docs.budgetpixel.com/api-reference/depth-maps/make-a-depth-map-with-video-depth-anything): a `video` (a public URL or an uploaded-file URL; up to 30 seconds, MP4, MOV or WebM, up to 100 MB). Poll [`GET /v1/depth-maps/{id}`](https://docs.budgetpixel.com/api-reference/depth-maps/get-depth-map-job-status) for the result. Job ids start with `dpt_`.
* `size`: `small` (the default, fastest), `base` (adds edge detail) or `large` (the finest detail and the steadiest).
* `colormap`: `grayscale` (the default), `turbo`, `inferno`, `magma` or `viridis`. `resolution`: `auto` (the default), `360p`, `480p`, `720p` or `1080p`. `keep_audio` and `side_by_side` (the input on the left, the depth map on the right) are off by default.
* The result is an H.264 MP4 at the input's frame size (up to 1080p) and frame rate (up to 30 fps). `video_url` is a short-lived signed URL, and the file is deleted 24 hours after generation.
* `GET /v1/models` lists the model with `type: "video-depth"` and a new `size_pricing` field, a map of each `size` to its credits per second: `{ "small": 20, "base": 30, "large": 40 }`. `POST /v1/cost` returns `credits_per_second`, `size_pricing` and `min_seconds`, plus the exact `credits` when you send `seconds`.

**Pricing.** Per second of the input video, rounded up to whole seconds, with a 5-second minimum: 20 credits for `small`, 30 for `base` and 40 for `large`. The price is the same at every `resolution`.

**MCP.** New tool: `generate_depth_map`.

Guide: [Depth maps API](https://docs.budgetpixel.com/apis/depth-maps-api.md).

**October 16, 2026**

## OmniHuman 2.0

The newest version of ByteDance's OmniHuman. It animates the person, character or pet in an image to speak your audio, with synchronized lips, expression and body motion, and camera movement you can direct with a prompt. OmniHuman 1.5 stays available.

* [`POST /v1/lip-sync/omni-human-2.0`](https://docs.budgetpixel.com/api-reference/lip-sync/lip-sync-with-omnihuman-20): an `image` and an `audio` clip, plus an optional `prompt` for the scene, gestures and camera (Chinese, English, Japanese, Korean, Spanish or Indonesian). Poll `GET /v1/lip-sync/{id}` for the video.
* 720p. Audio can be MP3, WAV or OGG, up to 120 seconds and 15 MB, twice the length OmniHuman 1.5 accepts. Images can be 300 to 6000 px a side, with an aspect ratio between 2:5 and 5:2.
* Lip-sync jobs on every model now reserve their quoted price when they're created, and the charge on success equals the quote from `POST /v1/cost`.

**Pricing.** 84 credits per second of audio, rounded up to whole seconds, with a 4-second minimum. OmniHuman 1.5 is 135 per second.

## FLUX 3 Video

Black Forest Labs' video model, with generated audio: sound effects, ambience, and dialogue with lip sync. It can also extend a clip you supply.

* [`POST /v1/videos/flux-3-video`](https://docs.budgetpixel.com/api-reference/black-forest-labs/generate-video-with-flux-3-video): text-to-video; image-to-video from a first frame, or a first and a last frame; and extension of your own MP4 or MOV (1 second to 2 minutes, up to 100 MB). An extension returns your clip followed by the new footage.
* 720p, 1080p, 1440p or 4K at 24 fps, 5 to 20 seconds. An extension adds 5 to 15 seconds.
* `generate_audio: false` makes a silent clip at the same price.

**Pricing.** Per second of output: 200 credits at 720p, 325 at 1080p, 380 at 1440p and 555 at 4K. Extensions cost 285, 365, 420 and 610 per new second.

**October 15, 2026**

## FLUX 3 Klein

A fast, low-cost version of FLUX 3 from Black Forest Labs, from 11 credits per image.

* [`POST /v1/images/flux-3-image-klein`](https://docs.budgetpixel.com/api-reference/black-forest-labs/generate-image-with-flux-3-klein): text-to-image and editing with up to 10 reference images (free), 1 to 4 images per request.
* 768px, 1K, 1.5K, 2K or 4K, with `aspect_ratio: auto` or one of 13 fixed ratios. It has no web grounding; use FLUX 3 for that.

**Pricing.** Per image: 11 credits at 768px, 12 at 1K, 15 at 1.5K, 19 at 2K and 48 at 4K.

## FLUX 3 Video Upscale

A second video upscaler next to Topaz: 1.5x to 3x, in a `precise` mode or a `creative` mode that adds detail.

* [`POST /v1/video-upscales/flux-3-video-upscale`](https://docs.budgetpixel.com/api-reference/upscaling/upscale-a-video-with-flux-3-video-upscale), then poll `GET /v1/video-upscales/{id}`.
* Input up to 20 seconds, 2560x1440 and 100 MB. `upscale_factor` is 1.5, 2, 2.5 or 3, with an optional `prompt`. The frame rate and audio are kept.

**Pricing.** Scales with the output's size and length: a 1080p result costs 188 credits per second in `precise` mode and 267 in `creative`.

**October 14, 2026**

## 3D models: Tripo H3.1 and Meshy 7.1

Turn one image into a textured 3D model you can download.

* [`POST /v1/3d/tripo-h3.1`](https://docs.budgetpixel.com/api-reference/3d-models/generate-a-3d-model-with-tripo-h31): the most faithful to the source image, cartoons included, as GLB with PBR materials. Options: `texture`, `texture_quality` (`standard` or `detailed`) and `detailed_geometry`.
* [`POST /v1/3d/meshy-7.1`](https://docs.budgetpixel.com/api-reference/3d-models/generate-a-3d-model-with-meshy-71): a lighter model (about 30K triangles) as GLB, FBX, USDZ and STL, with optional `rigging` and `animation` for humanoid characters.
* Poll [`GET /v1/3d/{job_id}`](https://docs.budgetpixel.com/api-reference/3d-models/get-3d-model-job-status) every 15 to 30 seconds; a model takes 2 to 5 minutes. Files are deleted after about 24 hours, so download them promptly.
* `GET /v1/models?type=3d` lists both models.

**Pricing.** Tripo H3.1: 400 credits textured, 270 without texture and 540 with detailed texture; detailed geometry adds 270. Meshy 7.1: 1600 credits textured and 1080 without texture; rigging adds 270 and animation 160.

**MCP.** New tool: `generate_3d_model`.

## P-Video 2 Pro

A low-cost video model from Pruna AI, with generated audio and a `mode` that trades cost against speed and quality.

* [`POST /v1/videos/p-video-2-pro`](https://docs.budgetpixel.com/api-reference/pruna-ai/generate-video-with-p-video-2-pro): text-to-video, and image-to-video from a first frame, a last frame, or both. 480p or 768p, 5 to 15 seconds, 24 fps.

**Pricing.** Per second of output at 480p: 15 credits in `cost` mode, 30 in `speed` and 60 in `quality`. At 768p: 37, 52 and 112.

**October 9, 2026**

## Stock sound effect and music search

Search BudgetPixel's free sound effect and background music libraries, licensed CC BY 4.0. Like stock image search, it works with keys on the Free plan.

* [`GET /v1/stock/sound-effects`](https://docs.budgetpixel.com/api-reference/stock-sound-effects/search-free-stock-sound-effects) and [`GET /v1/stock/music`](https://docs.budgetpixel.com/api-reference/stock-music/search-free-stock-music): filter by `query`, `category` (sound effects only), `min_duration`, `max_duration` and `sort`, up to 20 results per page.
* Each result carries a ready-made credit line (`attribution.text` and `attribution.html`) to include wherever you use it.
* Stock image search also gained `transparent=true`, for cut-outs with a transparent background.

**Pricing.** 10 credits per search, including searches with no results. These endpoints only search; they never generate.

**MCP.** New tool `search_stock_audio`, and `search_stock_images` now takes `transparent`.

Guides: [Stock sound effects](https://docs.budgetpixel.com/stock-sound-effects.md) and [Stock music](https://docs.budgetpixel.com/stock-music.md).

**October 6, 2026**

## Nano Banana 2.1

Google's image model, with sharper output and cleaner text in images than Nano Banana 2, and optional grounding in live web results.

* [`POST /v1/images/nano-banana-2.1`](https://docs.budgetpixel.com/api-reference/google/generate-image-with-nano-banana-21): text-to-image and editing with up to 9 reference images (free), 1 to 4 images per request, at 1K, 2K or 4K.
* `google_search` grounds the image in live Google Search results; `image_search` lets the model look at web images first. Both are off by default.

**Pricing.** Per image: 45 credits at 1K, 70 at 2K and 150 at 4K. `google_search` adds 10 credits per image, and `image_search` adds 20 in total, with or without `google_search`.

## Licenses on posts

[`POST /v1/posts`](https://docs.budgetpixel.com/api-reference/social/publish-a-post) takes a `license`: `arr` (All Rights Reserved, the default), `cc-by` (CC BY 4.0) or `cc0` (CC0 1.0). It can't be changed after publishing.

**MCP.** `create_social_post` takes `license`.

**October 4, 2026**

## FLUX 3

Black Forest Labs' FLUX 3: text-to-image and editing with up to 10 reference images.

* [`POST /v1/images/flux-3-image`](https://docs.budgetpixel.com/api-reference/black-forest-labs/generate-image-with-flux-3): 1 to 4 images per request at 768px, 1K, 1.5K, 2K or 4K. Reference images are free.
* `grounding` lets the model research the prompt with web and image search before rendering. It's on by default and costs nothing extra; set it to `false` for faster, self-contained generation.
* `GET /v1/models` now lists per-size prices for image models (`resolution_pricing`).

**Pricing.** Per image: 55 credits at 768px, 65 at 1K, 90 at 1.5K, 130 at 2K and 790 at 4K.

**September 29, 2026**

## SeeDream 5.0 Flash

ByteDance's fast, low-cost image model, typically done in under 20 seconds.

* [`POST /v1/images/seedream-5.0-flash`](https://docs.budgetpixel.com/api-reference/bytedance/generate-image-with-seedream-50-flash): text-to-image and editing with up to 10 reference images (free), 1 to 4 images per request, at 1K or 2K.
* `background: transparent` keeps a transparent background when you edit a single PNG cut-out, and returns a PNG with an alpha channel. SeeDream 5.0 Pro accepts it too.

**Pricing.** A flat 25 credits per image.

**September 24, 2026**

## MiniMax H3 Max

MiniMax's H3 tuned for stronger prompt adherence and looks, with native audio, reference clips and extension.

* [`POST /v1/videos/minimax-h3-max`](https://docs.budgetpixel.com/api-reference/minimax/generate-video-with-minimax-h3-max): text-to-video; image-to-video from a start and/or end frame; reference-to-video with up to 5 images, 3 video clips and 3 audio clips; and extension of a video you supply.
* 480p, 768p or 1080p (2K when extending), 5 to 15 seconds.

**Pricing.** Per second of output: 65 credits at 480p, 105 at 768p, 210 at 1080p and 420 at 2K. Input video is also billed per second, and each reference image beyond two adds 50; `POST /v1/cost` gives the exact figure.

**September 23, 2026**

## Stock image search

Search BudgetPixel's free stock image library, licensed CC BY 4.0. Keys on the Free plan can call it; the rest of the API needs a paid plan.

* [`GET /v1/stock/images`](https://docs.budgetpixel.com/api-reference/stock-images/search-free-stock-images): filter by `query`, `category`, `orientation`, `color`, `type` and `sort`, up to 20 results per page. Each result carries a credit line to use with the image.

**Pricing.** 10 credits per search, including searches with no results.

**MCP.** New tool: `search_stock_images`.

## SeeDance 1.5 Pro retired

SeeDance 1.5 Pro has been retired. Requests to `POST /v1/videos/seedance-1.5-pro` now return `410 model_retired`; use `seedance-2.0` instead. See [Retired models](https://docs.budgetpixel.com/concepts/models.md#retired-models).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.