Skip to main content
Everything that changed in the REST API, the MCP server, and the content verification API. Dates are when the change reached production.
apimcpvideoimages

Kling 4.0 video engine and Ideogram vectorization

  • Kling 4.0 — new video engine kling_4_0 on POST /videos/generations, in GET /videos/models, and on the MCP generate_video tool. All three modes: image_to_video (with an optional end frame), text_to_video, and text_to_video_styled.
  • Durations — every whole second from 3 to 30. The MCP tool uses 5 when you omit duration; the REST API requires it, as for every engine.
  • Resolution and aspect ratio — 720p (default) or 1080p; 16:9, 9:16, or 1:1. In image_to_video, the video follows the framing of the start image.
  • Audio — a soundtrack is always generated, at no extra cost.
  • Credits — 15 per second at 720p, 25 per second at 1080p (a 5 s clip is 75 / 125). text_to_video_styled adds the usual flat 10.
  • Vectorization engines — POST /images/vectorizations and the MCP vectorize_image tool have a new optional engine: recraft (default) or ideogram. With ideogram, the optional mode is default (detailed) or simple. A request without engine works as before. An unknown value, or a mode without ideogram, returns 422 before any charge.
  • Vectorization credits stay at 5 for every engine and mode. A cached result (0 credits) now counts only when it comes from the same engine and mode.
Kling 4.0 · Vectorize an image · Pricing · MCP tools
apimcpimages

Image uploads, Magic Edit engines, and terminal job status

  • Image uploads — new. Upload a local image file and get an image_id in three steps: POST /images/uploads/prepare (send the exact size_bytes) → PUT the file to the presigned upload_url (valid 1 hour) → POST /images/uploads/{image_id}/complete. JPEG, PNG, or WebP; up to 10 MB and 32 MP; at most 20 uploads awaiting completion per user. Free. Needs any one of images.edit, images.transform, or videos.generate — no new scope. The image_id works as the source of edits, image operations, and image-to-video.
  • MCP — two new free tools, prepare_image_upload and complete_image_upload, do the same. The server now has eighteen tools.
  • Magic Edit engines — POST /images/edits and the MCP edit_image tool now also accept nano_banana_2 and nano_banana_2_1, next to nano_banana_pro (default), gemini, and kontext. resolution (1K / 2K / 4K) works on the three Nano Banana engines, at 5 / 10 / 20 credits per output; gemini and kontext stay at a fixed resolution and 5 credits.
  • MCP edit_image — new optional resolution and num_images parameters. Before, MCP edits always ran at 1K.
  • Edit response — the 202 now echoes the effective engine and resolution.
  • Behaviour change: trained models with another engine — trained models and a color palette in an edit work only with nano_banana_pro. A request that names another engine together with them now returns 422 before any charge. Before, such a request was silently switched to nano_banana_pro.
  • Terminal job status for compliance blocks — an image job whose outputs all failed the compliance pipeline (for example C2PA signing) now ends failed with error delivery_blocked_compliance: <codes>, instead of staying processing. A job with some deliverable outputs is completed and lists the others in the new blocked_images field. This applies to the REST job GETs and the MCP get_job_status tool.
  • 4K outputs — C2PA signing of large (4K) outputs works again, so 4K images are delivered again.
Image Uploads · Image Editing · Compliance blocks · MCP tools
apimcpimages

Text-to-image engines

POST /images/generations and the MCP generate_image tool now accept seven text-to-image engines. The default stays nano_banana_pro; a request without engine behaves as before.
  • Engines — nano_banana_pro (default), nano_banana_2_1, nano_banana_2, and new: nano_banana, imagen_4, seedream_4, flux_1_pro. Each engine has its own aspect ratios and resolutions, validated before any charge (422).
  • GET /images/models — new. Lists the engines you can use, with aspect ratios, resolutions, num_outputs limit, credits per image, and trained-model support. Free, scope images.generate.
  • MCP — generate_image has a new optional engine parameter. This replaces the earlier note that generate_image always uses the default engine. The new free tool list_image_engines returns the same content as GET /images/models.
  • Trained models and palettes work with nano_banana_pro, nano_banana_2_1, and nano_banana_2. On the other engines they return 422 — never dropped.
  • Credits are the same on every engine: 5 per output at 1K, ×2 at 2K, ×4 at 4K.
  • Behaviour change for organizations restricted to trained models — they get an empty engine list (unavailable_reason: "organization_restricted"), any engine returns 422, and a request must omit engine and pass at least one trained model or a palette.
Image Generation · List image engines · MCP tools
apimcpimages

Nano Banana 2.1

A new image engine, nano_banana_2_1 (Nano Banana 2.1), is available next to nano_banana_pro and nano_banana_2.
  • POST /images/generations and POST /images/img2img accept engine: "nano_banana_2_1". The default engine stays nano_banana_pro.
  • MCP — the img2img tool accepts engine: "nano_banana_2_1". At this release, generate_image had no engine parameter and always used the default; it has one now (see Text-to-image engines above).
  • Same aspect ratios as nano_banana_2 (img2img also allows 4:1, 1:4, 8:1, 1:8), resolutions 1K, 2K, and 4K, and up to 14 img2img sources.
  • Same credits as nano_banana_2: 5 per output at 1K, ×2 at 2K, ×4 at 4K.
  • Not available for Magic Edit (POST /images/edits) or the MCP edit_image tool — both return 422.
Image Generation · Transform images (img2img)
apimcpimages

Image operations

Six ways to transform an image you already have, each an async POST that submits a job plus a GET that polls it.
  • POST /images/img2img · GET /images/img2img/{img2img_id} — transform 1–14 source images with a prompt.
  • POST /images/variations · GET /images/variations/{variation_id} — creative variations of one image, targeted at the whole frame, a person, an object, or the scene.
  • POST /images/resizes · GET /images/resizes/{resize_id} — change aspect ratio by outpainting rather than cropping.
  • POST /images/upscales · GET /images/upscales/{upscale_id} — upscale to a higher resolution across four models.
  • POST /images/background-removals · GET /images/background-removals/{background_removal_id} — cut the background to a transparent PNG.
  • POST /images/vectorizations · GET /images/vectorizations/{vectorization_id} — trace an image to SVG.
New scope. Variations, resizes, upscales, background removals, and vectorizations require images.transform. Img2img runs under the existing images.edit. Existing keys created with all scopes already carry it; a narrowed key needs the scope added in Settings → API Keys.Also in MCP. The same six operations are available as the img2img, create_variations, resize_image, upscale_image, remove_background, and vectorize_image tools.Pricing. Background removal costs 1 credit and vectorization 5, both 0 on a cache hit for a source already processed. The rest bill at 5 × resolution × outputs; upscale bills by target tier times a per-model multiplier. Image Operations · Pricing
content-verification

Hosted image watermark decode

The content verification API now decodes both image watermark techniques itself, rather than reporting them as unchecked.
  • TrustMark Q — the legacy corpus, covering images marked while TrustMark was the embed vendor. This lane stays available for that corpus permanently.
  • Meta PixelSeal — the current image watermark carried by newly generated Samsa images.
Watermarks remain corroboration only: the detected verdict still comes from C2PA manifest verification, which is authoritative. Video watermark decode (Meta Video Seal) is not yet available and is reported as not_checked — a technique that was never evaluated, never a false negative. Content verification
content-verification

Content verification API

A free, unauthenticated API for checking whether an image or video was made with Samsa — Samsa’s public detection mechanism under Article 50(2) of the EU AI Act. It has its own base URL, takes no API key, and spends no credits.
  • POST /v1/public/detect — check one uploaded image or video.
  • GET /v1/public/detect/info — machine-readable description of each marking technique and how to detect it.
  • GET /v1/public/detect/result/{request_id} — signed PDF of a past result.
  • GET /v1/public/detect/health — service status and version.
Content verification
mcp

Trained models by name, palettes, and inline previews

Three changes that make the MCP tools easier to drive from a conversation, where a model’s name is at hand but its id is not.
  • Names resolve like ids. style_id, object_ids, person_ids, and setting_ids accept a trained model’s name or id; a name resolves to a model visible to the connected credential.
  • color_palette — a new parameter on generate_image and edit_image, also given as a name or an id.
  • edit_image reached parity with generate_image, accepting all four trained-model reference parameters so an edit stays on-brand.
  • get_job_status returns a preview. A completed raster image job now carries a downscaled inline image alongside the link to the full-resolution asset, so clients can render the result directly. Vectorization returns SVG and has no raster preview.
MCP server
apimcplaunch

The Samsa public API and MCP server

The first public release. Samsa’s image and video studio — and your organization’s trained models — over a REST API and a remote MCP server.
  • Images — POST /images/generations and POST /images/edits, composing your organization’s trained style, object, person, and setting models.
  • Video — POST /videos/generations from a start frame, from text, or from text styled with your models, plus GET /videos/models for the engine list.
  • Model training — POST /models, POST /models/prepare, POST /models/{model_id}/complete, and GET /models/{model_id}/status.
  • Models — list, retrieve, update, and delete at /models.
  • Account — GET /me, GET /credits, and GET /usage.
Organization API keys. Scoped, shown once at creation, and acting for the key’s organization — credits come from that organization’s pool.Webhooks. Pass a webhook_url to be notified on completion instead of polling. Callbacks are signed, and failures retry at 5s, 30s, 2m, 15m, and 1h.MCP server. A remote Streamable-HTTP server at https://api.samsa.ai/mcp, taking either OAuth 2.1 for interactive clients such as Claude and ChatGPT or an API key for headless ones. Samsa API · Quickstart · MCP server